LLM Landscape Papers (Citation ≥ 150)

Generated: 2026-08-03 13:58:40
Source: Semantic Scholar API and local topic inference — Computer Science papers only
Total papers: 706

Topic Coverage

LLM Overview & History: 147
Multimodal LLMs: 128
Reasoning in LLMs: 114
Efficient LLMs: Training & Inference: 111
Instruction Tuning & SFT: 79
LLM Agents: 75
Prompt Engineering & In-Context Learning: 71
RLVR & Process Reward Models: 70
Alignment & RLHF: 65
Evaluation of LLMs & Agents: 61
LLM Architecture Innovations: 56
Self-Supervised & Representation Learning: 54
Data for LLMs: 53
Inference-Time Scaling & Test-Time Compute: 52
PEFT & LoRA: 50
Hallucination in LLMs: 43
GraphRAG & Knowledge Graphs: 39
Scaling Laws: 39
Federated & Personalized AI: 35
LLMs for Code: 35
RLAIF & Constitutional AI: 35
Retrieval-Augmented Generation (RAG): 34
Trustworthy & Secure LLMs: 34
LLMs for Healthcare & Science: 32
Continual Learning & Model Merging: 29
LLM Memory & Personalization: 27
Tabular Data & NL2SQL: 26
Embeddings & Vector Search: 24
Function Calling & Tool Use: 24
LLM for Robotics & Embodied AI: 24
Context Engineering: 20
LLMOps & Model Serving: 17
Mixture of Experts: 16
Small Language Models: 11
GUI Agents: 8
AIOps & Observability: 1

Papers

Training language models to follow instructions with human feedback📑: Making language models bigger does not inherently make them better at following a user's intent. [Mar 2022] (Citations: 22,017; Topics: Alignment & RLHF, Instruction Tuning & SFT, RLAIF & Constitutional AI)
LoRA: Low-Rank Adaptation of Large Language Models📑: An important paradigm of natural language processing consists of large-scale pre-training on general domain data and adaptation to particular tasks or domains. [Jun 2021] (Citations: 20,380; Topics: PEFT & LoRA, Data for LLMs)
Chain of Thought Prompting Elicits Reasoning in Large Language Models📑: We explore how generating a chain of thought -- a series of intermediate reasoning steps -- significantly improves the ability of large language models to perform complex reasoning. [Jan 2022] (Citations: 19,596; Topics: Reasoning in LLMs, Prompt Engineering & In-Context Learning, Inference-Time Scaling & Test-Time Compute)
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks📑: Large pre-trained language models have been shown to store factual knowledge in their parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks. [May 2020] (Citations: 15,276; Topics: Retrieval-Augmented Generation (RAG), GraphRAG & Knowledge Graphs, Context Engineering)
Towards Deep Learning Models Resistant to Adversarial Attacks📑: Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorrectly by the ... [Jun 2017] (Citations: 14,977; Topics: Trustworthy & Secure LLMs, Data for LLMs, Scaling Laws)
Evaluating Large Language Models Trained on Code📑: We introduce Codex, a GPT language model fine-tuned on publicly available code from GitHub, and study its Python code-writing capabilities. [Jul 2021] (Citations: 10,250; Topics: LLMs for Code)
Visual Instruction Tuning📑: Instruction tuning large language models (LLMs) using machine-generated instruction-following data has improved zero-shot capabilities on new tasks, but the idea is less explored in the multimodal ... [Apr 2023] (Citations: 10,077; Topics: Instruction Tuning & SFT, Multimodal LLMs, Data for LLMs)
Emerging Properties in Self-Supervised Vision Transformers📑: In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) [16] that stand out compared to convolutional networks (convnets). [Apr 2021] (Citations: 9,470; Topics: Self-Supervised & Representation Learning, Continual Learning & Model Merging, Multimodal LLMs)
Direct Preference Optimization: Your Language Model is Secretly a Reward Model📑: While large-scale unsupervised language models (LMs) learn broad world knowledge and some reasoning skills, achieving precise control of their behavior is difficult due to the completely unsupervised ... [May 2023] (Citations: 9,378; Topics: Alignment & RLHF, Reasoning in LLMs, RLVR & Process Reward Models)
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning📑: We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. [Jun 2020] (Citations: 8,701; Topics: Self-Supervised & Representation Learning, Multimodal LLMs, Instruction Tuning & SFT)
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models📑: The cost of vision-and-language pre-training has become increasingly prohibitive due to end-to-end training of large-scale models. [Jan 2023] (Citations: 8,420; Topics: Multimodal LLMs)
Scaling Laws for Neural Language Models📑: We study empirical scaling laws for language model performance on the cross-entropy loss. [Jan 2020] (Citations: 8,363; Topics: Scaling Laws, Inference-Time Scaling & Test-Time Compute)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces📑: Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. [Dec 2023] (Citations: 7,757; Topics: LLM Architecture Innovations, LLM Overview & History, Multimodal LLMs)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations📑: Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. [Sep 2019] (Citations: 7,544; Topics: Self-Supervised & Representation Learning, Scaling Laws, Instruction Tuning & SFT)
ReAct: Synergizing Reasoning and Acting in Language Models📑: While large language models (LLMs) have demonstrated impressive capabilities across tasks in language understanding and interactive decision making, their abilities for reasoning (e. [Oct 2022] (Citations: 7,423; Topics: Reasoning in LLMs)
Large Language Models are Zero-Shot Reasoners📑: Pretrained large language models (LLMs) are widely used in many sub-fields of natural language processing (NLP) and generally known as excellent few-shot learners with task-specific exemplars. [May 2022] (Citations: 7,395; Topics: Prompt Engineering & In-Context Learning, Instruction Tuning & SFT)
Self-Consistency Improves Chain of Thought Reasoning in Language Models📑: Chain-of-thought prompting combined with pre-trained large language models has achieved encouraging results on complex reasoning tasks. [Mar 2022] (Citations: 7,043; Topics: Reasoning in LLMs, Inference-Time Scaling & Test-Time Compute, Prompt Engineering & In-Context Learning)
Efficient Memory Management for Large Language Model Serving with PagedAttention📑: High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. [Sep 2023] (Citations: 6,745; Topics: Efficient LLMs: Training & Inference, LLMOps & Model Serving, LLM Architecture Innovations)
Parameter-Efficient Transfer Learning for NLP📑: Fine-tuning large pre-trained models is an effective transfer mechanism in NLP. [Feb 2019] (Citations: 6,743; Topics: PEFT & LoRA, Efficient LLMs: Training & Inference, Instruction Tuning & SFT)
On the Opportunities and Risks of Foundation Models📑: AI is undergoing a paradigm shift with the rise of models (e. [Aug 2021] (Citations: 6,725; Topics: LLM Overview & History)
The Power of Scale for Parameter-Efficient Prompt Tuning📑: In this work, we explore “prompt tuning,” a simple yet effective mechanism for learning “soft prompts” to condition frozen language models to perform specific downstream tasks. [Apr 2021] (Citations: 5,698; Topics: PEFT & LoRA, Prompt Engineering & In-Context Learning, Efficient LLMs: Training & Inference)
RoFormer: Enhanced Transformer with Rotary Position Embedding📑: Position encoding recently has shown effective in the transformer architecture. [Apr 2021] (Citations: 5,674; Topics: LLM Architecture Innovations, Embeddings & Vector Search)
DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning📑: General reasoning represents a long-standing and formidable challenge in artificial intelligence (AI). [Jan 2025] (Citations: 5,388; Topics: Reasoning in LLMs, RLVR & Process Reward Models, Federated & Personalized AI)
Survey of Hallucination in Natural Language Generation📑: Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. [Feb 2022] (Citations: 4,913; Topics: Hallucination in LLMs, LLM Overview & History, Multimodal LLMs)
QLoRA: Efficient Finetuning of Quantized LLMs📑: We present QLoRA, an efficient finetuning approach that reduces memory usage enough to finetune a 65B parameter model on a single 48GB GPU while preserving full 16-bit finetuning task performance. [May 2023] (Citations: 4,902; Topics: PEFT & LoRA, Efficient LLMs: Training & Inference, LLMOps & Model Serving)
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness📑: Transformers are slow and memory-hungry on long sequences, since the time and memory complexity of self-attention are quadratic in sequence length. [May 2022] (Citations: 4,620; Topics: Efficient LLMs: Training & Inference, LLM Architecture Innovations, LLM Memory & Personalization)
A Survey of Large Language Models📑: The rapid evolution of large language models (LLMs) has driven a transformative shift in artificial intelligence (AI), reshaping both research paradigms and practical applications. [Mar 2023] (Citations: 4,612; Topics: LLM Overview & History, Federated & Personalized AI)
Large language models encode clinical knowledge📑: Med-PaLM, a state-of-the-art large language model for medicine, is introduced and evaluated across several medical question answering tasks, demonstrating the promise of these models in this domain. [Dec 2022] (Citations: 4,532; Topics: LLMs for Healthcare & Science, GraphRAG & Knowledge Graphs, Tabular Data & NL2SQL)
Toolformer: Language Models Can Teach Themselves to Use Tools📑: Language models (LMs) exhibit remarkable abilities to solve new tasks from just a few examples or textual instructions, especially at scale. [Feb 2023] (Citations: 4,440; Topics: Function Calling & Tool Use, Instruction Tuning & SFT)
Transformer-XL: Attentive Language Models beyond a Fixed-Length Context📑: Transformers have a potential of learning longer-term dependency, but are limited by a fixed-length context in the setting of language modeling. [Jan 2019] (Citations: 4,382; Topics: Prompt Engineering & In-Context Learning, Self-Supervised & Representation Learning)
Tree of Thoughts: Deliberate Problem Solving with Large Language Models📑: Language models are increasingly being deployed for general problem solving across a wide range of tasks, but are still confined to token-level, left-to-right decision-making processes during ... [May 2023] (Citations: 4,342; Topics: Reasoning in LLMs, RLVR & Process Reward Models)
Sparks of Artificial General Intelligence: Early experiments with GPT-4📑: Artificial intelligence (AI) researchers have been developing and refining large language models (LLMs) that exhibit remarkable capabilities across a variety of domains and tasks, challenging our ... [Mar 2023] (Citations: 4,241; Topics: LLM Overview & History, Federated & Personalized AI)
Scaling Instruction-Finetuned Language Models📑: Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. [Oct 2022] (Citations: 4,236; Topics: Instruction Tuning & SFT, Data for LLMs, Scaling Laws)
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning📑 (Citations: 4,192; Topics: Reasoning in LLMs, RLVR & Process Reward Models, RLAIF & Constitutional AI)
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity📑: In deep learning, models typically reuse the same parameters for all inputs. [Jan 2021] (Citations: 4,177; Topics: Efficient LLMs: Training & Inference, PEFT & LoRA, Multimodal LLMs)
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback📑: We apply preference modeling and reinforcement learning from human feedback (RLHF) to ﬁnetune language models to act as helpful and harmless assistants. [Apr 2022] (Citations: 4,175; Topics: Alignment & RLHF, RLAIF & Constitutional AI, RLVR & Process Reward Models)
Learning to Prompt for Vision-Language Models📑: Large pre-trained vision-language models like CLIP have shown great potential in learning representations that are transferable across a wide range of downstream tasks. [Sep 2021] (Citations: 4,069; Topics: Multimodal LLMs, Prompt Engineering & In-Context Learning, Self-Supervised & Representation Learning)
Program Synthesis with Large Language Models📑: This paper explores the limits of the current generation of large language models for program synthesis in general purpose programming languages. [Aug 2021] (Citations: 3,938; Topics: LLMs for Code)
A Time Series is Worth 64 Words: Long-term Forecasting with Transformers📑: We propose an efficient design of Transformer-based models for multivariate time series forecasting and self-supervised representation learning. [Nov 2022] (Citations: 3,809; Topics: Self-Supervised & Representation Learning, Efficient LLMs: Training & Inference, LLM Memory & Personalization)
BEiT: BERT Pre-Training of Image Transformers📑: We introduce a self-supervised vision representation model BEiT, which stands for Bidirectional Encoder representation from Image Transformers. [Jun 2021] (Citations: 3,730; Topics: Self-Supervised & Representation Learning, Multimodal LLMs, Efficient LLMs: Training & Inference)
Let's Verify Step by Step📑: In recent years, large language models have greatly improved in their ability to perform complex multi-step reasoning. [May 2023] (Citations: 3,698; Topics: Reasoning in LLMs, RLVR & Process Reward Models)
Emergent Abilities of Large Language Models📑: Scaling up language models has been shown to predictably improve performance and sample efficiency on a wide range of downstream tasks. [Jun 2022] (Citations: 3,638; Topics: Scaling Laws)
Continual Lifelong Learning with Neural Networks: A Review📑: Humans and animals have the ability to continually acquire, fine-tune, and transfer knowledge and skills throughout their lifespan. [Feb 2018] (Citations: 3,563; Topics: Continual Learning & Model Merging, GraphRAG & Knowledge Graphs, PEFT & LoRA)
Retrieval-Augmented Generation for Large Language Models: A Survey📑: Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. [Dec 2023] (Citations: 3,557; Topics: Retrieval-Augmented Generation (RAG), Hallucination in LLMs, Reasoning in LLMs)
A Survey on Evaluation of Large Language Models📑: Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications. [Jul 2023] (Citations: 3,485; Topics: Evaluation of LLMs & Agents, LLM Overview & History)
Training Compute-Optimal Large Language Models📑: We investigate the optimal model size and number of tokens for training a transformer language model under a given compute budget. [Mar 2022] (Citations: 3,448; Topics: Scaling Laws, Inference-Time Scaling & Test-Time Compute)
Self-Instruct: Aligning Language Models with Self-Generated Instructions📑: Large “instruction-tuned” language models (i. [Dec 2022] (Citations: 3,374; Topics: Instruction Tuning & SFT)
Universal and Transferable Adversarial Attacks on Aligned Language Models📑: Because"out-of-the-box"large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to prevent undesirable ... [Jul 2023] (Citations: 3,259; Topics: Trustworthy & Secure LLMs)
Constitutional AI: Harmlessness from AI Feedback📑: As AI systems become more capable, we would like to enlist their help to supervise other AIs. [Dec 2022] (Citations: 3,239; Topics: RLAIF & Constitutional AI, Alignment & RLHF)
MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models📑: The recent GPT-4 has demonstrated extraordinary multi-modal abilities, such as directly generating websites from handwritten text and identifying humorous elements within images. [Apr 2023] (Citations: 3,194; Topics: Multimodal LLMs)
A survey on large language model based autonomous agents📑: Autonomous agents have long been a research focus in academic and industry communities. [Aug 2023] (Citations: 3,193; Topics: LLM Agents, LLM Overview & History, LLM Memory & Personalization)
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions📑: The emergence of large language models (LLMs) has marked a significant breakthrough in natural language processing (NLP), fueling a paradigm shift in information acquisition. [Nov 2023] (Citations: 3,152; Topics: Hallucination in LLMs, LLM Overview & History, Retrieval-Augmented Generation (RAG))
Barlow Twins: Self-Supervised Learning via Redundancy Reduction📑: Self-supervised learning (SSL) is rapidly closing the gap with supervised methods on large computer vision benchmarks. [Mar 2021] (Citations: 3,053; Topics: Self-Supervised & Representation Learning, Evaluation of LLMs & Agents, Multimodal LLMs)
Intern VL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks📑: The exponential growth of large language models (LLMs) has opened up numerous possibilities for multi-modal AGI systems. [Dec 2023] (Citations: 3,030; Topics: LLM Overview & History, Multimodal LLMs)
PaLM-E: An Embodied Multimodal Language Model📑: Large language models excel at a wide range of complex tasks. [Mar 2023] (Citations: 2,826; Topics: Multimodal LLMs, LLM for Robotics & Embodied AI)
Align before Fuse: Vision and Language Representation Learning with Momentum Distillation📑: Large-scale vision and language representation learning has shown promising improvements on various vision-language tasks. [Jul 2021] (Citations: 2,802; Topics: Multimodal LLMs, Self-Supervised & Representation Learning, Efficient LLMs: Training & Inference)
Visual Prompt Tuning📑: The current modus operandi in adapting pre-trained models involves updating all the backbone parameters, ie, full fine-tuning. [Mar 2022] (Citations: 2,670; Topics: PEFT & LoRA, Prompt Engineering & In-Context Learning, Instruction Tuning & SFT)
OpenVLA: An Open-Source Vision-Language-Action Model📑: Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rather than training ... [Jun 2024] (Citations: 2,580; Topics: LLM for Robotics & Embodied AI, Multimodal LLMs, Prompt Engineering & In-Context Learning)
VMamba: Visual State Space Model📑: Designing computationally efficient network architectures remains an ongoing necessity in computer vision. [Jan 2024] (Citations: 2,484; Topics: LLM Architecture Innovations, Efficient LLMs: Training & Inference)
A Continual Learning Survey: Defying Forgetting in Classification Tasks📑: Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. (Citations: 2,398; Topics: Continual Learning & Model Merging, LLM Overview & History, GraphRAG & Knowledge Graphs)
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone📑: We introduce phi-3-mini, a 3.8 billion parameter language model trained on 3.3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of ... [Apr 2024] (Citations: 2,275; Topics: Evaluation of LLMs & Agents, Small Language Models, LLM Overview & History)
Self-Supervised Learning: Generative or Contrastive📑: Deep supervised learning has achieved great success in the last decade. [Jun 2020] (Citations: 2,184; Topics: Self-Supervised & Representation Learning, Multimodal LLMs, Instruction Tuning & SFT)
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond📑: In this work, we introduce the Qwen-VL series, a set of large-scale vision-language models (LVLMs) designed to perceive and understand both texts and images. [Aug 2023] (Citations: 2,162; Topics: Multimodal LLMs)
DAPO: An Open-Source LLM Reinforcement Learning System at Scale📑: Inference scaling empowers LLMs with unprecedented reasoning ability, with reinforcement learning as the core technique to elicit complex reasoning. [Mar 2025] (Citations: 2,106; Topics: Reasoning in LLMs, RLVR & Process Reward Models, Efficient LLMs: Training & Inference)
Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?📑: Large language models (LMs) are able to in-context learn—perform a new task via inference alone by conditioning on a few input-label pairs (demonstrations) and making predictions for new inputs. [Feb 2022] (Citations: 2,059; Topics: Prompt Engineering & In-Context Learning, Efficient LLMs: Training & Inference, Inference-Time Scaling & Test-Time Compute)
π0: A Vision-Language-Action Flow Model for General Robot Control📑: Robot learning holds tremendous promise to unlock the full potential of flexible, general, and dexterous robot systems, as well as to address some of the deepest questions in artificial intelligence. [Oct 2024] (Citations: 2,048; Topics: LLM for Robotics & Embodied AI, Multimodal LLMs, Federated & Personalized AI)
Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling📑: How do large language models (LLMs) develop and evolve over the course of training? [Apr 2023] (Citations: 1,970; Topics: LLM Overview & History)
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters📑: Enabling LLMs to improve their outputs by using more test-time computation is a critical step towards building generally self-improving agents that can operate on open-ended natural language. [Aug 2024] (Citations: 1,903; Topics: Inference-Time Scaling & Test-Time Compute, LLM Agents, Reasoning in LLMs)
Voyager: An Open-Ended Embodied Agent with Large Language Models📑: We introduce Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human ... [May 2023] (Citations: 1,891; Topics: Continual Learning & Model Merging, LLM Agents, LLM for Robotics & Embodied AI)
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model📑: Recently the state space models (SSMs) with efficient hardware-aware designs, i. [Jan 2024] (Citations: 1,887; Topics: LLM Architecture Innovations, Self-Supervised & Representation Learning, Efficient LLMs: Training & Inference)
Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation📑: Program synthesis has been long studied with recent approaches focused on directly using the power of Large Language Models (LLMs) to generate code. [May 2023] (Citations: 1,873; Topics: LLMs for Code, LLM Overview & History, Evaluation of LLMs & Agents)
Improving Factuality and Reasoning in Language Models through Multiagent Debate📑: Large language models (LLMs) have demonstrated remarkable capabilities in language generation, understanding, and few-shot learning in recent years. [May 2023] (Citations: 1,846; Topics: Prompt Engineering & In-Context Learning, Reasoning in LLMs, LLM Agents)
LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day📑: Conversational generative AI has demonstrated remarkable promise for empowering biomedical practitioners, but current investigations focus on unimodal text. [Jun 2023] (Citations: 1,840; Topics: LLMs for Healthcare & Science, RLAIF & Constitutional AI)
The Rise and Potential of Large Language Model Based Agents: A Survey📑: For a long time, humanity has pursued artificial intelligence (AI) equivalent to or surpassing the human level, with AI agents considered a promising vehicle for this pursuit. [Sep 2023] (Citations: 1,829; Topics: LLM Agents, LLM Overview & History, LLM Memory & Personalization)
Solving Quantitative Reasoning Problems with Language Models📑: Language models have achieved remarkable performance on a wide range of tasks that require natural language understanding. [Jun 2022] (Citations: 1,812; Topics: Reasoning in LLMs, RLVR & Process Reward Models)
ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs📑: Despite the advancements of open-source large language models (LLMs), e. [Jul 2023] (Citations: 1,789; Topics: LLM Overview & History)
BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models📑: We introduce BitFit, a sparse-finetuning method where only the bias-terms of the model (or a subset of them) are being modified. [Jun 2021] (Citations: 1,780; Topics: PEFT & LoRA, Self-Supervised & Representation Learning, Efficient LLMs: Training & Inference)
Evaluating Object Hallucination in Large Vision-Language Models📑: Inspired by the superior language abilities of large language models (LLM), large vision-language models (LVLM) have been recently explored by integrating powerful LLMs for improving the performance ... [May 2023] (Citations: 1,773; Topics: Multimodal LLMs, Hallucination in LLMs)
A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity📑: This paper proposes a framework for quantitatively evaluating interactive LLMs such as ChatGPT using publicly available data sets. [Feb 2023] (Citations: 1,755; Topics: Multimodal LLMs, Evaluation of LLMs & Agents, Reasoning in LLMs)
A Survey on Contrastive Self-supervised Learning📑: Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. [Nov 2020] (Citations: 1,754; Topics: Self-Supervised & Representation Learning, Data for LLMs, LLM Overview & History)
Improving language models by retrieving from trillions of tokens📑: We enhance auto-regressive language models by conditioning on document chunks retrieved from a large corpus, based on local similarity with preceding tokens. [Dec 2021] (Citations: 1,747; Topics: LLM Overview & History)
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code📑: Large Language Models (LLMs) applied to code-related applications have emerged as a prominent field, attracting significant interest from both academia and industry. [Mar 2024] (Citations: 1,744; Topics: Evaluation of LLMs & Agents, LLMs for Code)
A Comprehensive Overview of Large Language Models📑: Large Language Models (LLMs) have recently demonstrated remarkable capabilities in natural language processing tasks and beyond. [Jul 2023] (Citations: 1,725; Topics: LLM Overview & History)
DeepSeek-Coder: When the Large Language Model Meets Programming - The Rise of Code Intelligence📑: The rapid development of large language models has revolutionized code intelligence in software development. [Jan 2024] (Citations: 1,717; Topics: LLMs for Code)
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models📑: Large language models (LLMs) show excellent performance but are compute- and memory-intensive. [Nov 2022] (Citations: 1,693; Topics: Efficient LLMs: Training & Inference, LLM Memory & Personalization, Alignment & RLHF)
Fast Inference from Transformers via Speculative Decoding📑: Inference from large autoregressive models like Transformers is slow - decoding K tokens takes K serial runs of the model. [Nov 2022] (Citations: 1,686; Topics: Efficient LLMs: Training & Inference)
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts📑: Large Language Models (LLMs) and Large Multimodal Models (LMMs) exhibit impressive problem-solving skills in many tasks and domains, but their ability in mathematical reasoning in visual contexts has ... [Oct 2023] (Citations: 1,682; Topics: Multimodal LLMs, LLM Overview & History, Reasoning in LLMs)
From Local to Global: A Graph RAG Approach to Query-Focused Summarization📑: The use of retrieval-augmented generation (RAG) to retrieve relevant information from an external knowledge source enables large language models (LLMs) to answer questions over private and/or ... [Apr 2024] (Citations: 1,666; Topics: Retrieval-Augmented Generation (RAG), GraphRAG & Knowledge Graphs, Function Calling & Tool Use)
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality📑: While Transformers have been the main architecture behind deep learning's success in language modeling, state-space models (SSMs) such as Mamba have recently been shown to match or outperform ... [May 2024] (Citations: 1,632; Topics: LLM Architecture Innovations, Efficient LLMs: Training & Inference, Multimodal LLMs)
MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models📑: Multimodal Large Language Model (MLLM) relies on the powerful LLM to perform multimodal tasks, showing amazing emergent abilities in recent studies, such as writing poems based on an image. [Jun 2023] (Citations: 1,615; Topics: Evaluation of LLMs & Agents, Multimodal LLMs, Scaling Laws)
ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools📑: We introduce ChatGLM, an evolving family of large language models that we have been developing over time. [Jun 2024] (Citations: 1,598; Topics: Function Calling & Tool Use, Inference-Time Scaling & Test-Time Compute)
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time📑: The conventional recipe for maximizing model accuracy is to (1) train multiple models with various hyperparameters and (2) pick the individual model which performs best on a held-out validation set ... [Mar 2022] (Citations: 1,592; Topics: Continual Learning & Model Merging, Efficient LLMs: Training & Inference, Inference-Time Scaling & Test-Time Compute)
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling📑: We introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series that builds upon InternVL 2.0, maintaining its core model architecture while introducing significant enhancements ... [Dec 2024] (Citations: 1,560; Topics: Inference-Time Scaling & Test-Time Compute, Multimodal LLMs, Data for LLMs)
CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society📑: The rapid advancement of chat-based language models has led to remarkable progress in complex task-solving. [Mar 2023] (Citations: 1,550; Topics: LLM Agents)
GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints📑: Multi-query attention (MQA), which only uses a single key-value head, drastically speeds up decoder inference. [May 2023] (Citations: 1,544; Topics: LLM Architecture Innovations, Efficient LLMs: Training & Inference)
Unifying Large Language Models and Knowledge Graphs: A Roadmap📑: Large language models (LLMs), such as ChatGPT and GPT4, are making new waves in the field of natural language processing and artificial intelligence, due to their emergent ability and ... [Jun 2023] (Citations: 1,530; Topics: GraphRAG & Knowledge Graphs, LLM Overview & History, Federated & Personalized AI)
Jailbreaking Black Box Large Language Models in Twenty Queries📑: There is growing interest in ensuring that large language models (LLMs) align with human values. [Oct 2023] (Citations: 1,520; Topics: Trustworthy & Secure LLMs)
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models📑: We introduce InternVL3, a significant advancement in the InternVL series featuring a native multimodal pre-training paradigm. [Apr 2025] (Citations: 1,494; Topics: Inference-Time Scaling & Test-Time Compute, Multimodal LLMs, Reasoning in LLMs)
AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration📑: Large language models (LLMs) have transformed numerous AI applications. [Jun 2023] (Citations: 1,480; Topics: Efficient LLMs: Training & Inference, Small Language Models)
Reproducible Scaling Laws for Contrastive Language-Image Learning📑: Scaling up neural networks has led to remarkable performance across a wide range of tasks. [Dec 2022] (Citations: 1,465; Topics: Scaling Laws, Self-Supervised & Representation Learning, Multimodal LLMs)
A survey on multimodal large language models📑: ABSTRACT Recently, the multimodal large language model (MLLM) represented by GPT-4V has been a new rising research hotspot, which uses powerful large language models (LLMs) as a brain to perform ... [Jun 2023] (Citations: 1,451; Topics: Multimodal LLMs, LLM Overview & History)
Scaling Vision Transformers📑: Attention-based neural networks such as the Vision Transformer (ViT) have recently attained state-of-the-art results on many computer vision benchmarks. [Jun 2021] (Citations: 1,446; Topics: Evaluation of LLMs & Agents, LLM Architecture Innovations, Scaling Laws)
Large Language Models Are Human-Level Prompt Engineers📑: By conditioning on natural language instructions, large language models (LLMs) have displayed impressive capabilities as general-purpose computers. [Nov 2022] (Citations: 1,436; Topics: Prompt Engineering & In-Context Learning, Instruction Tuning & SFT)
Graph of Thoughts: Solving Elaborate Problems with Large Language Models📑: We introduce Graph of Thoughts (GoT): a framework that advances prompting capabilities in large language models (LLMs) beyond those offered by paradigms such as Chain-of-Thought or Tree of Thoughts ... [Aug 2023] (Citations: 1,408; Topics: Reasoning in LLMs, Prompt Engineering & In-Context Learning, Inference-Time Scaling & Test-Time Compute)
Detecting hallucinations in large language models using semantic entropy📑: Large language model (LLM) systems, such as ChatGPT1 or Gemini2, can show impressive reasoning and question-answering capabilities but often ‘hallucinate’ false outputs and unsubstantiated answers3,4. (Citations: 1,390; Topics: Hallucination in LLMs, Reasoning in LLMs, LLM Overview & History)
Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning📑: Few-shot in-context learning (ICL) enables pre-trained language models to perform a previously-unseen task without any gradient-based training by feeding a small number of training examples as part ... [May 2022] (Citations: 1,352; Topics: Prompt Engineering & In-Context Learning, PEFT & LoRA, Efficient LLMs: Training & Inference)
SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot📑: We show for the first time that large-scale generative pretrained transformer (GPT) family models can be pruned to at least 50% sparsity in one-shot, without any retraining, at minimal loss of ... [Jan 2023] (Citations: 1,352; Topics: Mixture of Experts, LLM Architecture Innovations, Inference-Time Scaling & Test-Time Compute)
Gorilla: Large Language Model Connected with Massive APIs📑: Large Language Models (LLMs) have seen an impressive wave of advances recently, with models now excelling in a variety of tasks, such as mathematical reasoning and program synthesis. [May 2023] (Citations: 1,343; Topics: LLMs for Code, Reasoning in LLMs, Multimodal LLMs)
LIMA: Less Is More for Alignment📑: Large language models are trained in two stages: (1) unsupervised pretraining from raw text, to learn general-purpose representations, and (2) large scale instruction tuning and reinforcement ... [May 2023] (Citations: 1,332; Topics: Instruction Tuning & SFT, Alignment & RLHF, Self-Supervised & Representation Learning)
s1: Simple test-time scaling📑: Test-time scaling is a promising new approach to language modeling that uses extra test-time compute to improve performance. [Jan 2025] (Citations: 1,324; Topics: Inference-Time Scaling & Test-Time Compute, Reasoning in LLMs, Scaling Laws)
VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning📑: Recent self-supervised methods for image representation learning are based on maximizing the agreement between embedding vectors from different views of the same image. [May 2021] (Citations: 1,299; Topics: Self-Supervised & Representation Learning, Embeddings & Vector Search, Multimodal LLMs)
Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting📑: Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). [May 2023] (Citations: 1,284; Topics: Reasoning in LLMs, Prompt Engineering & In-Context Learning, Inference-Time Scaling & Test-Time Compute)
mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality📑: Large language models (LLMs) have demonstrated impressive zero-shot abilities on a variety of open-ended tasks, while recent research has also explored the use of LLMs for multi-modal generation. [Apr 2023] (Citations: 1,256; Topics: Multimodal LLMs, Instruction Tuning & SFT)
Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!📑: Optimizing large language models (LLMs) for downstream use cases often involves the customization of pre-trained LLMs through further fine-tuning. [Oct 2023] (Citations: 1,245; Topics: Trustworthy & Secure LLMs, PEFT & LoRA, Instruction Tuning & SFT)
GLaM: Efficient Scaling of Language Models with Mixture-of-Experts📑: Scaling language models with more data, compute and parameters has driven significant progress in natural language processing. [Dec 2021] (Citations: 1,241; Topics: Mixture of Experts, Efficient LLMs: Training & Inference, Data for LLMs)
Inference-Time Intervention: Eliciting Truthful Answers from a Language Model📑: We introduce Inference-Time Intervention (ITI), a technique designed to enhance the"truthfulness"of large language models (LLMs). [Jun 2023] (Citations: 1,240; Topics: Inference-Time Scaling & Test-Time Compute, Efficient LLMs: Training & Inference)
Kosmos-2: Grounding Multimodal Large Language Models to the World📑: We introduce Kosmos-2, a Multimodal Large Language Model (MLLM), enabling new capabilities of perceiving object descriptions (e. [Jun 2023] (Citations: 1,222; Topics: Multimodal LLMs)
Towards a Unified View of Parameter-Efficient Transfer Learning📑: Fine-tuning large pre-trained language models on downstream tasks has become the de-facto learning paradigm in NLP. [Oct 2021] (Citations: 1,211; Topics: PEFT & LoRA, Efficient LLMs: Training & Inference, Instruction Tuning & SFT)
Teaching Large Language Models to Self-Debug📑: Large language models (LLMs) have achieved impressive performance on code generation. [Apr 2023] (Citations: 1,173; Topics: LLMs for Code, Instruction Tuning & SFT)
Parameter-efficient fine-tuning of large-scale pre-trained language models📑: With the prevalence of pre-trained language models (PLMs) and the pre-training–fine-tuning paradigm, it has been continuously shown that larger models tend to yield better performance. (Citations: 1,161; Topics: PEFT & LoRA, Efficient LLMs: Training & Inference, Instruction Tuning & SFT)
Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning📑: Efficiently acquiring external knowledge and up-to-date information is essential for effective reasoning and text generation in large language models (LLMs). [Mar 2025] (Citations: 1,160; Topics: Reasoning in LLMs, Efficient LLMs: Training & Inference, RLVR & Process Reward Models)
Bias and Fairness in Large Language Models: A Survey📑: Abstract Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation of human-like text, with increasing integration into systems that touch our ... [Sep 2023] (Citations: 1,157; Topics: LLM Overview & History, Retrieval-Augmented Generation (RAG))
A General Language Assistant as a Laboratory for Alignment📑: Given the broad capabilities of large language models, it should be possible to work towards a general-purpose, text-based assistant that is aligned with human values, meaning that it is helpful ... [Dec 2021] (Citations: 1,147; Topics: Alignment & RLHF)
S3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization📑: Recently, significant progress has been made in sequential recommendation with deep learning. [Aug 2020] (Citations: 1,134; Topics: Self-Supervised & Representation Learning, Multimodal LLMs, Instruction Tuning & SFT)
Understanding R1-Zero-Like Training: A Critical Perspective📑: DeepSeek-R1-Zero has shown that reinforcement learning (RL) at scale can directly enhance the reasoning capabilities of LLMs without supervised fine-tuning. [Mar 2025] (Citations: 1,118; Topics: Reasoning in LLMs, RLVR & Process Reward Models, PEFT & LoRA)
RWKV: Reinventing RNNs for the Transformer Era📑: Transformers have revolutionized almost all natural language processing (NLP) tasks but suffer from memory and computational complexity that scales quadratically with sequence length. [May 2023] (Citations: 1,104; Topics: LLM Architecture Innovations, LLM Memory & Personalization, Prompt Engineering & In-Context Learning)
Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions📑: Prompting-based large language models (LLMs) are surprisingly powerful at generating natural language reasoning steps or Chains-of-Thoughts (CoT) for multi-step question answering (QA). [Dec 2022] (Citations: 1,082; Topics: Reasoning in LLMs, Prompt Engineering & In-Context Learning, GraphRAG & Knowledge Graphs)
Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation📑: Contrastive learning has shown remarkable success in the field of multimodal representation learning. [Nov 2022] (Citations: 1,078; Topics: Self-Supervised & Representation Learning, Multimodal LLMs)
Accurate predictions on small data with a tabular foundation model📑: Tabular data, spreadsheets organized in rows and columns, are ubiquitous across scientific fields, from biomedicine to particle physics to economics and climate science1,2. (Citations: 1,076; Topics: LLMs for Healthcare & Science, Tabular Data & NL2SQL, Data for LLMs)
Towards artificial general intelligence with hybrid Tianjic chip architecture📑 (Citations: 1,074; Topics: LLM Architecture Innovations, Federated & Personalized AI)
Scaling Vision with Sparse Mixture of Experts📑: Sparsely-gated Mixture of Experts networks (MoEs) have demonstrated excellent scalability in Natural Language Processing. [Jun 2021] (Citations: 1,073; Topics: Mixture of Experts)
Large Language Models Can Be Easily Distracted by Irrelevant Context📑: Large language models have achieved impressive performance on various natural language processing tasks. [Feb 2023] (Citations: 1,062; Topics: LLM Overview & History)
Simplified State Space Layers for Sequence Modeling📑: Models using structured state space sequence (S4) layers have achieved state-of-the-art performance on long-range sequence modeling tasks. [Aug 2022] (Citations: 1,052; Topics: LLM Architecture Innovations)
Reasoning with Language Model is Planning with World Model📑: Large language models (LLMs) have shown remarkable reasoning capabilities, especially when prompted to generate intermediate reasoning steps (e. [May 2023] (Citations: 1,049; Topics: Reasoning in LLMs, LLM Agents, Prompt Engineering & In-Context Learning)
Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models📑: While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs ... [Sep 2023] (Citations: 1,041; Topics: Hallucination in LLMs, LLM Overview & History)
Mathematical discoveries from program search with large language models📑: Large language models (LLMs) have demonstrated tremendous capabilities in solving complex tasks, from quantitative reasoning to understanding natural language. (Citations: 1,033; Topics: Reasoning in LLMs, Multimodal LLMs)
RULER: What's the Real Context Size of Your Long-Context Language Models?📑: The needle-in-a-haystack (NIAH) test, which examines the ability to retrieve a piece of information (the"needle") from long distractor texts (the"haystack"), has been widely adopted to evaluate ... [Apr 2024] (Citations: 1,033; Topics: Context Engineering)
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention📑: We present LLaMA-Adapter, a lightweight adaption method to efficiently fine-tune LLaMA into an instruction-following model. [Mar 2023] (Citations: 1,029; Topics: Instruction Tuning & SFT, PEFT & LoRA, LLM Architecture Innovations)
SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models📑: Generative Large Language Models (LLMs) such as GPT-3 are capable of generating highly fluent responses to a wide variety of user prompts. [Mar 2023] (Citations: 1,028; Topics: Hallucination in LLMs, Prompt Engineering & In-Context Learning, LLM Overview & History)
Autonomous chemical research with large language models📑: Transformer-based large language models are making significant strides in various fields, such as natural language processing^ 1 – 5 , biology^ 6 , 7 , chemistry^ 8 – 10 and computer programming^ 11 ... (Citations: 1,027; Topics: LLMs for Healthcare & Science, LLM Agents)
Time-LLM: Time Series Forecasting by Reprogramming Large Language Models📑: Time series forecasting holds significant importance in many real-world dynamic systems and has been extensively studied. [Oct 2023] (Citations: 1,026; Topics: Inference-Time Scaling & Test-Time Compute)
Augmenting large language models with chemistry tools📑: Large language models (LLMs) have shown strong performance in tasks across domains but struggle with chemistry-related problems. [Apr 2023] (Citations: 1,005; Topics: LLMs for Healthcare & Science, Function Calling & Tool Use)
Large Language Models: A Survey📑: Large Language Models (LLMs) have drawn a lot of attention due to their strong performance on a wide range of natural language tasks, since the release of ChatGPT in November 2022. [Feb 2024] (Citations: 1,004; Topics: LLM Overview & History, LLM Architecture Innovations, Efficient LLMs: Training & Inference)
A Survey on Large Language Models for Code Generation📑: Large Language Models (LLMs) have garnered remarkable advancements across diverse code-related tasks, known as Code LLMs, particularly in code generation that generates source code with LLM from ... [Jun 2024] (Citations: 996; Topics: LLMs for Code, LLM Overview & History)
Towards Understanding Sycophancy in Language Models📑: Human feedback is commonly utilized to finetune AI assistants. [Oct 2023] (Citations: 995; Topics: Alignment & RLHF, Hallucination in LLMs, RLAIF & Constitutional AI)
Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models📑: In this work, we introduce the Qwen3 Embedding series, a significant advancement over its predecessor, the GTE-Qwen series, in text embedding and reranking capabilities, built upon the Qwen3 ... [Jun 2025] (Citations: 994; Topics: LLM Overview & History, Embeddings & Vector Search)
WizardCoder: Empowering Code Large Language Models with Evol-Instruct📑: Code Large Language Models (Code LLMs), such as StarCoder, have demonstrated exceptional performance in code-related tasks. [Jun 2023] (Citations: 991; Topics: LLMs for Code)
Large Language Model based Multi-Agents: A Survey of Progress and Challenges📑: Large Language Models (LLMs) have achieved remarkable success across a wide array of tasks. [Feb 2024] (Citations: 991; Topics: LLM Agents, LLM Overview & History)
Automatic Chain of Thought Prompting in Large Language Models📑: Large language models (LLMs) can perform complex reasoning by generating intermediate reasoning steps. [Oct 2022] (Citations: 990; Topics: Reasoning in LLMs, Prompt Engineering & In-Context Learning, Inference-Time Scaling & Test-Time Compute)
Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey📑: Large models represent a groundbreaking advancement in multiple application fields, enabling remarkable achievements across various tasks. [Mar 2024] (Citations: 967; Topics: PEFT & LoRA, Efficient LLMs: Training & Inference, LLM Overview & History)
Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data📑: One of the defining properties of deep learning is that models are chosen to have many more parameters than available training data. [Mar 2017] (Citations: 960; Topics: Data for LLMs, Scaling Laws, GraphRAG & Knowledge Graphs)
SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension📑: Based on powerful Large Language Models (LLMs), recent generative Multimodal Large Language Models (MLLMs) have gained prominence as a pivotal research area, exhibiting remarkable capability for both ... [Jul 2023] (Citations: 953; Topics: Evaluation of LLMs & Agents, Multimodal LLMs, LLM Overview & History)
Instruction-Following Evaluation for Large Language Models📑: One core capability of Large Language Models (LLMs) is to follow natural language instructions. [Nov 2023] (Citations: 953; Topics: Instruction Tuning & SFT, Evaluation of LLMs & Agents)
BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset📑: In this paper, we introduce the \textsc{BeaverTails} dataset, aimed at fostering research on safety alignment in large language models (LLMs). [Jul 2023] (Citations: 945; Topics: Alignment & RLHF, Data for LLMs, Trustworthy & Secure LLMs)
A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models📑: As one of the most advanced techniques in AI, Retrieval-Augmented Generation (RAG) can offer reliable and up-to-date external knowledge, providing huge convenience for numerous tasks. [May 2024] (Citations: 941; Topics: Retrieval-Augmented Generation (RAG), LLM Overview & History, Function Calling & Tool Use)
A Watermark for Large Language Models📑: Potential harms of large language models can be mitigated by watermarking model output, i. [Jan 2023] (Citations: 939; Topics: LLM Overview & History)
MTEB: Massive Text Embedding Benchmark📑: Text embeddings are commonly evaluated on a small set of datasets from a single task not covering their possible applications to other tasks. [Oct 2022] (Citations: 925; Topics: Embeddings & Vector Search, Evaluation of LLMs & Agents, Data for LLMs)
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models📑: In the era of large language models, Mixture-of-Experts (MoE) is a promising architecture for managing computational costs when scaling up model parameters. [Jan 2024] (Citations: 922; Topics: Mixture of Experts, LLM Architecture Innovations)
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback📑: Reinforcement learning from human feedback (RLHF) is a technique for training AI systems to align with human goals. [Jul 2023] (Citations: 915; Topics: Alignment & RLHF, RLAIF & Constitutional AI, RLVR & Process Reward Models)
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery📑: One of the grand challenges of artificial general intelligence is developing agents capable of conducting scientific research and discovering new knowledge. [Aug 2024] (Citations: 913; Topics: LLM Agents, Federated & Personalized AI, LLMs for Healthcare & Science)
Ignore Previous Prompt: Attack Techniques For Language Models📑: Transformer-based large language models (LLMs) provide a powerful foundation for natural language tasks in large-scale customer-facing applications. [Nov 2022] (Citations: 912; Topics: Prompt Engineering & In-Context Learning, Efficient LLMs: Training & Inference, LLMs for Code)
A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications📑: Prompt engineering has emerged as an indispensable technique for extending the capabilities of large language models (LLMs) and vision-language models (VLMs). [Feb 2024] (Citations: 907; Topics: Prompt Engineering & In-Context Learning, Multimodal LLMs, LLM Overview & History)
RegionCLIP: Region-based Language-Image Pretraining📑: Contrastive language-image pretraining (CLIP) using image-text pairs has achieved impressive results on image classification in both zero-shot and transfer learning set-tings. [Dec 2021] (Citations: 897; Topics: Self-Supervised & Representation Learning, Multimodal LLMs, Instruction Tuning & SFT)
SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities📑: Understanding and reasoning about spatial relationships is a fundamental capability for Visual Question Answering (VQA) and robotics. [Jan 2024] (Citations: 881; Topics: LLM for Robotics & Embodied AI, Multimodal LLMs, Reasoning in LLMs)
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs📑: We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach. [Jun 2024] (Citations: 875; Topics: Multimodal LLMs)
LLM-Pruner: On the Structural Pruning of Large Language Models📑: Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. [May 2023] (Citations: 870; Topics: Efficient LLMs: Training & Inference)
Yi: Open Foundation Models by 01.AI📑: We introduce the Yi model family, a series of language and multimodal models that demonstrate strong multi-dimensional capabilities. [Mar 2024] (Citations: 852; Topics: LLM Overview & History, Multimodal LLMs)
AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models📑: Evaluating the general abilities of foundation models to tackle human-level tasks is a vital aspect of their development and application in the pursuit of Artificial General Intelligence (AGI). [Apr 2023] (Citations: 850; Topics: Evaluation of LLMs & Agents, LLM Overview & History, Federated & Personalized AI)
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments📑: Autonomous agents that accomplish complex computer tasks with minimal human interventions have the potential to transform human-computer interaction, significantly enhancing accessibility and ... [Apr 2024] (Citations: 850; Topics: LLM Agents, Evaluation of LLMs & Agents, Multimodal LLMs)
Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers📑: The fundamental learning theory behind neural networks remains largely open. [Nov 2018] (Citations: 838; Topics: GraphRAG & Knowledge Graphs, Scaling Laws, Continual Learning & Model Merging)
KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation📑: Abstract Pre-trained language representation models (PLMs) cannot well capture factual knowledge from text. [Nov 2019] (Citations: 831; Topics: Embeddings & Vector Search)
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration📑 (Citations: 825; Topics: Efficient LLMs: Training & Inference)
AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models📑: The aligned Large Language Models (LLMs) are powerful language understanding and decision-making tools that are created through extensive alignment with human feedback. [Oct 2023] (Citations: 817; Topics: Alignment & RLHF, Prompt Engineering & In-Context Learning, Trustworthy & Secure LLMs)
A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT📑: Recently, ChatGPT, along with DALL-E-2 and Codex,has been gaining significant attention from society. [Mar 2023] (Citations: 804; Topics: LLM Overview & History, LLM Architecture Innovations, Efficient LLMs: Training & Inference)
TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data📑: Recent years have witnessed the burgeoning of pretrained language models (LMs) for text-based natural language (NL) understanding tasks. [May 2020] (Citations: 800; Topics: Tabular Data & NL2SQL, Data for LLMs)
Extending Context Window of Large Language Models via Positional Interpolation📑: We present Position Interpolation (PI) that extends the context window sizes of RoPE-based pretrained LLMs such as LLaMA models to up to 32768 with minimal fine-tuning (within 1000 steps), while ... [Jun 2023] (Citations: 796; Topics: Context Engineering, LLM Architecture Innovations, PEFT & LoRA)
Diffusion Model Alignment Using Direct Preference Optimization📑: Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. [Nov 2023] (Citations: 796; Topics: Alignment & RLHF, RLAIF & Constitutional AI, RLVR & Process Reward Models)
A Comparative Study on Transformer vs RNN in Speech Applications📑: Sequence-to-sequence models have been widely used in end-to-end speech processing, for example, automatic speech recognition (ASR), speech translation (ST), and text-to-speech (TTS). [Sep 2019] (Citations: 794; Topics: LLM Architecture Innovations)
TIES-Merging: Resolving Interference When Merging Models📑: Transfer learning - i.e., further fine-tuning a pre-trained model on a downstream task - can confer significant advantages, including improved downstream performance, faster convergence, and better ... [Jun 2023] (Citations: 793; Topics: Continual Learning & Model Merging, PEFT & LoRA, Instruction Tuning & SFT)
Aligning Large Multimodal Models with Factually Augmented RLHF📑: Large Multimodal Models (LMM) are built across modalities and the misalignment between two modalities can result in"hallucination", generating textual outputs that are not grounded by the multimodal ... [Sep 2023] (Citations: 790; Topics: Alignment & RLHF, Multimodal LLMs, Hallucination in LLMs)
CogAgent: A Visual Language Model for GUI Agents📑: People are spending an enormous amount of time on dig-ital devices through graphical user interfaces (GUIs), e. [Dec 2023] (Citations: 785; Topics: GUI Agents, LLM Agents, GraphRAG & Knowledge Graphs)
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs📑: In this paper, we present the VideoLLaMA 2, a set of Video Large Language Models (Video-LLMs) designed to enhance spatial-temporal modeling and audio understanding in video and audio-oriented tasks. [Jun 2024] (Citations: 784; Topics: Multimodal LLMs)
Solving math word problems with process- and outcome-based feedback📑: Recent work has shown that asking language models to generate reasoning steps improves performance on many reasoning tasks. [Nov 2022] (Citations: 784; Topics: Reasoning in LLMs, RLVR & Process Reward Models, Alignment & RLHF)
Towards Expert-Level Medical Question Answering with Large Language Models📑: Recent artificial intelligence (AI) systems have reached milestones in"grand challenges"ranging from Go to protein-folding. [May 2023] (Citations: 783; Topics: LLMs for Healthcare & Science, Tabular Data & NL2SQL, Federated & Personalized AI)
H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models📑: Large Language Models (LLMs), despite their recent impressive accomplishments, are notably cost-prohibitive to deploy, particularly for applications involving long-content generation, such as ... [Jun 2023] (Citations: 783; Topics: Efficient LLMs: Training & Inference, LLMOps & Model Serving, LLM Overview & History)
CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing📑: Recent developments in large language models (LLMs) have been impressive. [May 2023] (Citations: 778; Topics: Function Calling & Tool Use, LLM Overview & History, Instruction Tuning & SFT)
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads📑: Large Language Models (LLMs) employ auto-regressive decoding that requires sequential computation, with each step reliant on the previous one's output. [Jan 2024] (Citations: 774; Topics: Efficient LLMs: Training & Inference, Reasoning in LLMs, RLVR & Process Reward Models)
High-throughput Generative Inference of Large Language Models with a Single GPU📑: The high computational and memory requirements of large language model (LLM) inference make it feasible only with multiple high-end accelerators. [Mar 2023] (Citations: 762; Topics: LLM Memory & Personalization, Efficient LLMs: Training & Inference, LLM Architecture Innovations)
Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models📑: Large language models (LLMs) have recently been shown to deliver impressive performance in various NLP tasks. [May 2023] (Citations: 754; Topics: Reasoning in LLMs, Prompt Engineering & In-Context Learning, Inference-Time Scaling & Test-Time Compute)
Large Language Diffusion Models📑: The capabilities of large language models (LLMs) are widely regarded as relying on autoregressive models (ARMs). [Feb 2025] (Citations: 754; Topics: LLM Overview & History)
TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation📑: Large Language Models (LLMs) have demonstrated remarkable performance across diverse domains, thereby prompting researchers to explore their potential for use in recommendation systems. [May 2023] (Citations: 752; Topics: Prompt Engineering & In-Context Learning, Efficient LLMs: Training & Inference, PEFT & LoRA)
MAD-X: An Adapter-based Framework for Multi-task Cross-lingual Transfer📑: The main goal behind state-of-the-art pretrained multilingual models such as multilingual BERT and XLM-R is enabling and bootstrapping NLP applications in low-resource languages through zero-shot or ... [May 2020] (Citations: 749; Topics: PEFT & LoRA, LLM Overview & History, Instruction Tuning & SFT)
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies📑: The burgeoning interest in developing Large Language Models (LLMs) with up to trillion parameters has been met with concerns regarding resource efficiency and practical expense, particularly given ... [Apr 2024] (Citations: 738; Topics: Small Language Models)
DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving📑: DistServe improves the performance of large language models (LLMs) serving by disaggregating the prefill and decoding computation. [Jan 2024] (Citations: 730; Topics: Efficient LLMs: Training & Inference, LLMOps & Model Serving)
A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT📑: Pretrained Foundation Models (PFMs) are regarded as the foundation for various downstream tasks with different data modalities. [Feb 2023] (Citations: 728; Topics: LLM Overview & History, Data for LLMs)
DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction📑: We study the problem of decomposing a complex text-to-sql task into smaller sub-tasks and how such a decomposition can significantly improve the performance of Large Language Models (LLMs) in the ... [Apr 2023] (Citations: 727; Topics: Tabular Data & NL2SQL, Prompt Engineering & In-Context Learning, Self-Supervised & Representation Learning)
CodeT5+: Open Code Large Language Models for Code Understanding and Generation📑: Large language models (LLMs) pretrained on vast source code have achieved prominent progress in code intelligence. [May 2023] (Citations: 726; Topics: LLMs for Code, LLM Overview & History)
ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction📑: GNNs and chemical fingerprints are the predominant approaches to representing molecules for property prediction. [Oct 2020] (Citations: 726; Topics: Self-Supervised & Representation Learning, Instruction Tuning & SFT)
Safe RLHF: Safe Reinforcement Learning from Human Feedback📑: With the development of large language models (LLMs), striking a balance between the performance and safety of AI systems has never been more critical. [Oct 2023] (Citations: 726; Topics: Alignment & RLHF, RLVR & Process Reward Models, Trustworthy & Secure LLMs)
ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge📑: Objective The primary aim of this research was to address the limitations observed in the medical knowledge of prevalent large language models (LLMs) such as ChatGPT, by creating a specialized ... [Mar 2023] (Citations: 725; Topics: LLM Overview & History, LLMs for Healthcare & Science)
Masked Autoencoders for Point Cloud Self-supervised Learning📑: As a promising scheme of self-supervised learning, masked autoencoding has significantly advanced natural language processing and computer vision. [Mar 2022] (Citations: 723; Topics: Self-Supervised & Representation Learning, Multimodal LLMs, Instruction Tuning & SFT)
Baseline Defenses for Adversarial Attacks Against Aligned Language Models📑: As Large Language Models quickly become ubiquitous, it becomes critical to understand their security vulnerabilities. [Sep 2023] (Citations: 721; Topics: Trustworthy & Secure LLMs)
Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning📑 (Citations: 713; Topics: PEFT & LoRA, Efficient LLMs: Training & Inference, Instruction Tuning & SFT)
An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-Tuning📑: Catastrophic forgetting (CF) is a phenomenon that occurs in machine learning when a model forgets previously learned information while acquiring new knowledge for achieving satisfactory performance ... [Aug 2023] (Citations: 709; Topics: Continual Learning & Model Merging, PEFT & LoRA, Instruction Tuning & SFT)
Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding📑: Large Vision-Language Models (LVLMs) have advanced considerably, intertwining visual recognition and language understanding to generate content that is not only coherent but also contextually attuned. [Nov 2023] (Citations: 708; Topics: Hallucination in LLMs, Multimodal LLMs, Self-Supervised & Representation Learning)
FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance📑: There is a rapidly growing number of large language models (LLMs) that users can query for a fee. [May 2023] (Citations: 705; Topics: LLM Architecture Innovations)
Expectation vs. Experience: Evaluating the Usability of Code Generation Tools Powered by Large Language Models📑: Recent advances in Large Language Models (LLM) have made automatic code generation possible for real-world programming tasks in general-purpose programming languages such as Python. (Citations: 700; Topics: LLMs for Code, Function Calling & Tool Use)
Automatic Prompt Optimization with "Gradient Descent" and Beam Search📑: Large Language Models (LLMs) have shown impressive performance as general purpose agents, but their abilities remain highly dependent on prompts which are hand written with onerous trial-and-error ... [May 2023] (Citations: 699; Topics: LLM Agents, Prompt Engineering & In-Context Learning)
A Review on Large Language Models: Architectures, Applications, Taxonomies, Open Issues and Challenges📑: Large Language Models (LLMs) recently demonstrated extraordinary capability in various natural language processing (NLP) tasks including language translation, text generation, question answering, etc. (Citations: 692; Topics: LLM Architecture Innovations, LLM Overview & History, Retrieval-Augmented Generation (RAG))
Are Emergent Abilities of Large Language Models a Mirage?📑: Recent work claims that large language models display emergent abilities, abilities not present in smaller-scale models that are present in larger-scale models. [Apr 2023] (Citations: 691; Topics: Scaling Laws)
VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks📑: Large language models (LLMs) have notably accelerated progress towards artificial general intelligence (AGI), with their impressive zero-shot capacity for user-tailored tasks, endowing them with ... [May 2023] (Citations: 688; Topics: Federated & Personalized AI, Instruction Tuning & SFT)
SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities📑: Multi-modal large language models are regarded as a crucial step towards Artificial General Intelligence (AGI) and have garnered significant interest with the emergence of ChatGPT. [May 2023] (Citations: 679; Topics: LLM Overview & History, Federated & Personalized AI, Reasoning in LLMs)
RemoteCLIP: A Vision Language Foundation Model for Remote Sensing📑: General-purpose foundation models have led to recent breakthroughs in artificial intelligence (AI). [Jun 2023] (Citations: 678; Topics: Multimodal LLMs, LLM Overview & History, Federated & Personalized AI)
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets📑: In this paper we propose to study generalization of neural networks on small algorithmically generated datasets. [Jan 2022] (Citations: 673; Topics: Data for LLMs, Scaling Laws, GraphRAG & Knowledge Graphs)
RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback📑: Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences, but gathering high-quality preference labels is expensive. [Sep 2023] (Citations: 669; Topics: Alignment & RLHF, RLAIF & Constitutional AI, RLVR & Process Reward Models)
Efficiently Scaling Transformer Inference📑: We study the problem of efficient generative inference for Transformer models, in one of its most challenging settings: large deep models, with tight latency targets and long sequence lengths. [Nov 2022] (Citations: 668; Topics: Efficient LLMs: Training & Inference, LLMOps & Model Serving, LLM Architecture Innovations)
Hungry Hungry Hippos: Towards Language Modeling with State Space Models📑: State space models (SSMs) have demonstrated state-of-the-art sequence modeling performance in some modalities, but underperform attention in language modeling. [Dec 2022] (Citations: 663; Topics: LLM Architecture Innovations, Efficient LLMs: Training & Inference)
TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models📑: Text recognition is a long-standing research problem for document digitalization. [Sep 2021] (Citations: 659; Topics: LLM Architecture Innovations)
Enabling Large Language Models to Generate Text with Citations📑: Large language models (LLMs) have emerged as a widely-used tool for information seeking, but their generated outputs are prone to hallucination. [May 2023] (Citations: 657; Topics: Hallucination in LLMs, Function Calling & Tool Use)
Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation📑: Large language models (LLMs) have emerged as a new paradigm for Text-to-SQL task. [Aug 2023] (Citations: 651; Topics: Evaluation of LLMs & Agents, Tabular Data & NL2SQL, LLM Agents)
Eureka: Human-Level Reward Design via Coding Large Language Models📑: Large Language Models (LLMs) have excelled as high-level semantic planners for sequential decision-making tasks. [Oct 2023] (Citations: 646; Topics: RLVR & Process Reward Models)
Self-Rewarding Language Models📑: We posit that to achieve superhuman agents, future models require superhuman feedback in order to provide an adequate training signal. [Jan 2024] (Citations: 643; Topics: LLM Agents, Alignment & RLHF, RLAIF & Constitutional AI)
SLIP: Self-supervision meets Language-Image Pre-training📑: Recent work has shown that self-supervised pre-training leads to improvements over supervised learning on challenging visual recognition tasks. [Dec 2021] (Citations: 634; Topics: Self-Supervised & Representation Learning, Multimodal LLMs, Instruction Tuning & SFT)
Scalable Modified Kneser-Ney Language Model Estimation📑 (Citations: 632; Topics: LLM Overview & History)
GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts📑: Large language models (LLMs) have recently experienced tremendous popularity and are widely used from casual conversations to AI-driven programming. [Sep 2023] (Citations: 626; Topics: Trustworthy & Secure LLMs, Prompt Engineering & In-Context Learning)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models📑: In this work, we present a novel method to tackle the token generation challenge in Vision Language Models (VLMs) for video and image understanding, called LLaMA-VID. [Nov 2023] (Citations: 625; Topics: Multimodal LLMs)
Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces📑: Humans possess the visual-spatial intelligence to remember spaces from sequential visual observations. [Dec 2024] (Citations: 623; Topics: Multimodal LLMs, Inference-Time Scaling & Test-Time Compute)
SALMONN: Towards Generic Hearing Abilities for Large Language Models📑: Hearing is arguably an essential ability of artificial intelligence (AI) agents in the physical world, which refers to the perception and understanding of general auditory information consisting of ... [Oct 2023] (Citations: 621; Topics: LLM Agents, Federated & Personalized AI)
Sentiment Analysis in the Era of Large Language Models: A Reality Check📑: Sentiment analysis (SA) has been a long-standing research area in natural language processing. [May 2023] (Citations: 613; Topics: LLM Overview & History)
Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success📑: Recent vision-language-action models (VLAs) build upon pretrained vision-language models and leverage diverse robot datasets to demonstrate strong task execution, language following ability, and ... [Feb 2025] (Citations: 610; Topics: LLM for Robotics & Embodied AI, Multimodal LLMs, Data for LLMs)
Hallucination is Inevitable: An Innate Limitation of Large Language Models📑: Hallucination has been widely recognized to be a significant drawback for large language models (LLMs). [Jan 2024] (Citations: 608; Topics: Hallucination in LLMs, Tabular Data & NL2SQL)
Training Large Language Models to Reason in a Continuous Latent Space📑: Large language models (LLMs) are typically constrained to reason in the language space, where they express the reasoning process through a chain-of-thought (CoT) to solve complex problems. [Dec 2024] (Citations: 607; Topics: Reasoning in LLMs, Inference-Time Scaling & Test-Time Compute, Prompt Engineering & In-Context Learning)
A Survey on the Memory Mechanism of Large Language Model-based Agents📑: Large language model (LLM)-based agents have recently attracted much attention from the research and industry communities. [Apr 2024] (Citations: 604; Topics: LLM Agents, LLM Memory & Personalization, LLM Architecture Innovations)
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding📑: We present DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL, through two key major upgrades. [Dec 2024] (Citations: 599; Topics: Multimodal LLMs, Mixture of Experts)
Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve📑: Each LLM serving request goes through two phases. [Mar 2024] (Citations: 598; Topics: Efficient LLMs: Training & Inference, LLMOps & Model Serving)
ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation📑: Pre-trained models have achieved state-of-the-art results in various Natural Language Processing (NLP) tasks. [Jul 2021] (Citations: 597; Topics: GraphRAG & Knowledge Graphs, Hallucination in LLMs, Prompt Engineering & In-Context Learning)
Brain-inspired replay for continual learning with artificial neural networks📑: Artificial neural networks suffer from catastrophic forgetting. (Citations: 597; Topics: Continual Learning & Model Merging, GraphRAG & Knowledge Graphs, Scaling Laws)
Evaluating Very Long-Term Conversational Memory of LLM Agents📑: Existing works on long-term open-domain dialogues focus on evaluating model responses within contexts spanning no more than five chat sessions. [Feb 2024] (Citations: 596; Topics: LLM Memory & Personalization, LLM Agents, Context Engineering)
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think📑: Recent studies have shown that the denoising process in (generative) diffusion models can induce meaningful (discriminative) representations inside the model, though the quality of these ... [Oct 2024] (Citations: 594; Topics: Alignment & RLHF, Efficient LLMs: Training & Inference, Self-Supervised & Representation Learning)
Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models📑: DeepSeek-R1-Zero has successfully demonstrated the emergence of reasoning capabilities in LLMs purely through Reinforcement Learning (RL). [Mar 2025] (Citations: 590; Topics: Multimodal LLMs, Reasoning in LLMs, RLVR & Process Reward Models)
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models📑: We introduce DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance. The key technical breakthroughs of DeepSeek-V3.2 are as follows: (1) ... [Dec 2025] (Citations: 588; Topics: Reasoning in LLMs, LLM Agents, LLM Overview & History)
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models📑: Harnessing the power of human-annotated data through Supervised Fine-Tuning (SFT) is pivotal for advancing Large Language Models (LLMs). [Jan 2024] (Citations: 587; Topics: Instruction Tuning & SFT, Data for LLMs, PEFT & LoRA)
Scalable Extraction of Training Data from (Production) Language Models📑: This paper studies extractable memorization: training data that an adversary can efficiently extract by querying a machine learning model without prior knowledge of the training dataset. [Nov 2023] (Citations: 574; Topics: Data for LLMs, Efficient LLMs: Training & Inference, Tabular Data & NL2SQL)
Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning📑: Large Language Models (LLMs) have shown human-like reasoning abilities but still struggle with complex logical problems. [May 2023] (Citations: 571; Topics: Reasoning in LLMs, Alignment & RLHF)
YaRN: Efficient Context Window Extension of Large Language Models📑: Rotary Position Embeddings (RoPE) have been shown to effectively encode positional information in transformer-based language models. [Sep 2023] (Citations: 571; Topics: Context Engineering, Embeddings & Vector Search, LLM Architecture Innovations)
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models📑: Recent advancements in Large Language Models (LLMs) have sparked interest in their formal reasoning capabilities, particularly in mathematics. [Oct 2024] (Citations: 569; Topics: Reasoning in LLMs, Multimodal LLMs)
Augmented Language Models: a Survey📑: This survey reviews works in which language models (LMs) are augmented with reasoning skills and the ability to use tools. [Feb 2023] (Citations: 569; Topics: Reasoning in LLMs, LLM Overview & History, Function Calling & Tool Use)
Benchmarking Large Language Models in Retrieval-Augmented Generation📑: Retrieval-Augmented Generation (RAG) is a promising approach for mitigating the hallucination of large language models (LLMs). [Sep 2023] (Citations: 566; Topics: Retrieval-Augmented Generation (RAG), Evaluation of LLMs & Agents, Hallucination in LLMs)
Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment📑: Ensuring alignment, which refers to making models behave in accordance with human intentions [1,2], has become a critical task before deploying large language models (LLMs) in real-world applications. [Aug 2023] (Citations: 561; Topics: Alignment & RLHF, Trustworthy & Secure LLMs, LLM Overview & History)
Large-Scale Adversarial Training for Vision-and-Language Representation Learning📑: We present VILLA, the first known effort on large-scale adversarial training for vision-and-language (V+L) representation learning. [Jun 2020] (Citations: 555; Topics: Self-Supervised & Representation Learning, Trustworthy & Secure LLMs, Multimodal LLMs)
A Survey on Self-Supervised Learning: Algorithms, Applications, and Future Trends📑: Deep supervised learning algorithms typically require a large volume of labeled data to achieve satisfactory performance. [Jan 2023] (Citations: 547; Topics: Self-Supervised & Representation Learning, Data for LLMs, LLM Overview & History)
Benchmarking Retrieval-Augmented Generation for Medicine📑: While large language models (LLMs) have achieved state-of-the-art performance on a wide range of medical question answering (QA) tasks, they still face challenges with hallucinations and outdated ... [Feb 2024] (Citations: 543; Topics: Retrieval-Augmented Generation (RAG), Hallucination in LLMs, Evaluation of LLMs & Agents)
RRHF: Rank Responses to Align Language Models with Human Feedback without tears📑: Reinforcement Learning from Human Feedback (RLHF) facilitates the alignment of large language models with human preferences, significantly enhancing the quality of interactions between humans and ... [Apr 2023] (Citations: 541; Topics: Alignment & RLHF, RLAIF & Constitutional AI, RLVR & Process Reward Models)
High-dimensional dynamics of generalization error in neural networks📑: We perform an analysis of the average generalization dynamics of large neural networks trained using gradient descent. [Oct 2017] (Citations: 537; Topics: GraphRAG & Knowledge Graphs, Scaling Laws, Continual Learning & Model Merging)
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models📑: Jailbreak attacks cause large language models (LLMs) to generate harmful, unethical, or otherwise objectionable content. [Apr 2024] (Citations: 531; Topics: Evaluation of LLMs & Agents, Trustworthy & Secure LLMs, Instruction Tuning & SFT)
NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models📑: Decoder-only LLM-based embedding models are beginning to outperform BERT or T5-based embedding models in general-purpose text embedding tasks, including dense vector-based retrieval. [May 2024] (Citations: 529; Topics: Embeddings & Vector Search, Retrieval-Augmented Generation (RAG))
On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes📑: Knowledge distillation (KD) is widely used for compressing a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. [Jun 2023] (Citations: 529; Topics: Efficient LLMs: Training & Inference, LLM Memory & Personalization, Self-Supervised & Representation Learning)
Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting📑: Addressing catastrophic forgetting is one of the key challenges in continual learning where machine learning systems are trained with sequential or streaming tasks. [Apr 2019] (Citations: 528; Topics: Continual Learning & Model Merging)
A Survey on Multimodal Large Language Models for Autonomous Driving📑: With the emergence of Large Language Models (LLMs) and Vision Foundation Models (VFMs), multimodal AI systems benefiting from large models have the potential to equally perceive the real world, make ... [Nov 2023] (Citations: 528; Topics: LLM Overview & History, Multimodal LLMs, LLM Agents)
BLINK: Multimodal Large Language Models Can See but Not Perceive📑: We introduce Blink, a new benchmark for multimodal language models (LLMs) that focuses on core visual perception abilities not found in other evaluations. [Apr 2024] (Citations: 522; Topics: Evaluation of LLMs & Agents, Multimodal LLMs, LLM Agents)
Recommender Systems in the Era of Large Language Models (LLMs)📑: With the prosperity of e-commerce and web applications, Recommender Systems (RecSys) have become an indispensable and important component, providing personalized suggestions that cater to user ... [Jul 2023] (Citations: 521; Topics: LLM Memory & Personalization, Federated & Personalized AI)
OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation📑: Hallucination, posed as a pervasive challenge of multi-modal large language models (MLLMs), has significantly impeded their real-world usage that demands precise judgment. [Nov 2023] (Citations: 521; Topics: Hallucination in LLMs)
V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs📑: When we look around and perform complex tasks, how we see and selectively process what we see is crucial. [Dec 2023] (Citations: 520; Topics: Multimodal LLMs)
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs📑: The remarkable performance of models like the OpenAI o1 can be attributed to their ability to emulate human-like long-time thinking during inference. [Dec 2024] (Citations: 519; Topics: Inference-Time Scaling & Test-Time Compute, Efficient LLMs: Training & Inference)
AraVec: A set of Arabic Word Embedding Models for use in Arabic NLP📑: Abstract Advancements in neural networks have led to developments in fields like computer vision, speech recognition and natural language processing (NLP). (Citations: 515; Topics: Embeddings & Vector Search, Scaling Laws, GraphRAG & Knowledge Graphs)
An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation📑: Unit tests play a key role in ensuring the correctness of software. [Feb 2023] (Citations: 515; Topics: Evaluation of LLMs & Agents)
Parameter-Efficient Transfer Learning with Diff Pruning📑: The large size of pretrained networks makes them difficult to deploy for multiple tasks in storage-constrained settings. [Dec 2020] (Citations: 512; Topics: PEFT & LoRA, Efficient LLMs: Training & Inference, Continual Learning & Model Merging)
SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild📑: DeepSeek-R1 has shown that long chain-of-thought (CoT) reasoning can naturally emerge through a simple reinforcement learning (RL) framework with rule-based rewards, where the training may directly ... [Mar 2025] (Citations: 512; Topics: Reasoning in LLMs, RLVR & Process Reward Models, Inference-Time Scaling & Test-Time Compute)
GeDi: Generative Discriminator Guided Sequence Generation📑: While large-scale language models (LMs) are able to imitate the distribution of natural language well enough to generate realistic text, it is difficult to control which regions of the distribution ... [Sep 2020] (Citations: 511; Topics: Hallucination in LLMs, Efficient LLMs: Training & Inference, Retrieval-Augmented Generation (RAG))
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders📑: Large decoder-only language models (LLMs) are the state-of-the-art models on most of today's NLP tasks and benchmarks. [Apr 2024] (Citations: 510; Topics: Evaluation of LLMs & Agents, Prompt Engineering & In-Context Learning)
Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy📑: Large language models are powerful text processors and reasoners, but are still subject to limitations including outdated knowledge and hallucinations, which necessitates connecting them to the world. [May 2023] (Citations: 508; Topics: Retrieval-Augmented Generation (RAG), Hallucination in LLMs, Embeddings & Vector Search)
API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs📑: Recent research has demonstrated that Large Language Models (LLMs) can enhance their capabilities by utilizing external tools. [Apr 2023] (Citations: 508; Topics: Function Calling & Tool Use, Evaluation of LLMs & Agents)
FAST: Efficient Action Tokenization for Vision-Language-Action Models📑: Autoregressive sequence models, such as Transformer-based vision-language action (VLA) policies, can be tremendously effective for capturing complex and generalizable robotic behaviors. [Jan 2025] (Citations: 508; Topics: LLM for Robotics & Embodied AI, Multimodal LLMs, Efficient LLMs: Training & Inference)
An empirical analysis of compute-optimal large language model training📑 (Citations: 506; Topics: Scaling Laws, Inference-Time Scaling & Test-Time Compute)
Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning📑: Despite the promising progress in multi-modal tasks, current large multi-modal models (LMMs) are prone to hallucinating inconsistent descriptions with respect to the associated image and human ... [Jun 2023] (Citations: 505; Topics: Instruction Tuning & SFT, Hallucination in LLMs, Multimodal LLMs)
Causal Reasoning and Large Language Models: Opening a New Frontier for Causality📑: The causal capabilities of large language models (LLMs) are a matter of significant debate, with critical implications for the use of LLMs in societally impactful domains such as medicine, science ... [May 2023] (Citations: 504; Topics: LLMs for Healthcare & Science, Reasoning in LLMs)
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning📑: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models (LLMs), while its mechanisms are not yet well ... [Jun 2025] (Citations: 500; Topics: RLVR & Process Reward Models, Reasoning in LLMs, RLAIF & Constitutional AI)
REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments📑: One of the long-term challenges of robotics is to enable robots to interact with humans in the visual world via natural language, as humans are visual animals that communicate through language. [Apr 2019] (Citations: 496; Topics: LLM for Robotics & Embodied AI, LLM Memory & Personalization)
Visual-RFT: Visual Reinforcement Fine-Tuning📑: Reinforcement Fine-Tuning (RFT) in Large Reasoning Models like OpenAI ol learns from feedback on its answers, which is especially useful in applications when fine-tuning data is scarce. [Mar 2025] (Citations: 496; Topics: Reasoning in LLMs, Data for LLMs, Instruction Tuning & SFT)
BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains📑: Large Language Models (LLMs) have demonstrated remarkable versatility in recent years, offering potential applications across specialized domains such as healthcare and medicine. [Feb 2024] (Citations: 494; Topics: LLMs for Healthcare & Science, LLM Overview & History, Retrieval-Augmented Generation (RAG))
Aligning Large Language Models with Human: A Survey📑 (Citations: 492; Topics: LLM Overview & History)
VL-ADAPTER: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks📑: Recently, fine-tuning language models pre-trained on large text corpora have provided huge improvements on vision-and-language (V&L) tasks as well as on pure language tasks. [Dec 2021] (Citations: 492; Topics: PEFT & LoRA, Efficient LLMs: Training & Inference, Instruction Tuning & SFT)
Electrodialysis for water desalination: A critical assessment of recent developments on process fundamentals, models and applications📑 (Citations: 489; Topics: LLM Overview & History)
LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models📑: The success of large language models (LLMs), like GPT-4 and ChatGPT, has led to the development of numerous cost-effective and accessible alternatives that are created by finetuning open-access LLMs ... [Apr 2023] (Citations: 489; Topics: PEFT & LoRA, LLM Overview & History, Efficient LLMs: Training & Inference)
Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents📑: We investigate the challenge of task planning for multi-task embodied agents in open-world environments. [Feb 2023] (Citations: 488; Topics: LLM Agents, LLM for Robotics & Embodied AI, Function Calling & Tool Use)
Understanding Dimensional Collapse in Contrastive Self-supervised Learning📑: Self-supervised visual representation learning aims to learn useful representations without relying on human annotations. [Oct 2021] (Citations: 486; Topics: Self-Supervised & Representation Learning, Instruction Tuning & SFT, Alignment & RLHF)
Automatic Generation of Programming Exercises and Code Explanations Using Large Language Models📑: This article explores the natural language generation capabilities of large language models with application to the production of two types of learning resources common in programming courses. [Jun 2022] (Citations: 485; Topics: LLMs for Code, Hallucination in LLMs)
Jailbreak and Guard Aligned Language Models With Only Few In-Context Demonstrations📑: Large Language Models (LLMs) have demonstrated remarkable success across diverse applications, yet their susceptibility to malicious exploitation remains a critical challenge. [Oct 2023] (Citations: 485; Topics: Prompt Engineering & In-Context Learning, Trustworthy & Secure LLMs)
UI-TARS: Pioneering Automated GUI Interaction with Native Agents📑: This paper introduces UI-TARS, a native GUI agent model that solely perceives the screenshots as input and performs human-like interactions (e. [Jan 2025] (Citations: 485; Topics: GUI Agents, LLM Agents)
Larger language models do in-context learning differently📑: We study how in-context learning (ICL) in language models is affected by semantic priors versus input-label mappings. [Mar 2023] (Citations: 483; Topics: Prompt Engineering & In-Context Learning)
Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning📑: Anomaly detection on attributed networks attracts considerable research interests due to wide applications of attributed networks in modeling a wide range of complex systems. [Mar 2021] (Citations: 480; Topics: Self-Supervised & Representation Learning, AIOps & Observability, Instruction Tuning & SFT)
Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs📑: We introduce Phi-4-Mini and Phi-4-Multimodal, compact yet highly capable language and multimodal models. [Mar 2025] (Citations: 480; Topics: Multimodal LLMs, Small Language Models)
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding📑: In this paper, we propose VideoLLaMA3, a more advanced multimodal foundation model for image and video understanding. [Jan 2025] (Citations: 478; Topics: Multimodal LLMs, LLM Overview & History)
LaMP: When Large Language Models Meet Personalization📑: This paper highlights the importance of personalization in large language models and introduces the LaMP benchmark -- a novel benchmark for training and evaluating language models for producing ... [Apr 2023] (Citations: 477; Topics: Evaluation of LLMs & Agents, LLM Memory & Personalization, Federated & Personalized AI)
Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning📑: Large language models (LLMs) have been shown to be capable of impressive few-shot generalisation to new tasks. [May 2022] (Citations: 476; Topics: Reasoning in LLMs, Prompt Engineering & In-Context Learning, Efficient LLMs: Training & Inference)
ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search📑: Recent methodologies in LLM self-training mostly rely on LLM generating responses and filtering those with correct output answers as training data. [Jun 2024] (Citations: 476; Topics: RLVR & Process Reward Models, Reasoning in LLMs, Data for LLMs)
A systematic review on overfitting control in shallow and deep neural networks📑 (Citations: 471; Topics: GraphRAG & Knowledge Graphs, Scaling Laws, Continual Learning & Model Merging)
Editing Large Language Models: Problems, Methods, and Opportunities📑: Despite the ability to train capable LLMs, the methodology for maintaining their relevancy and rectifying errors remains elusive. [May 2023] (Citations: 468; Topics: LLM Overview & History)
A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models📑: As Large Language Models (LLMs) continue to advance in their ability to write human-like text, a key challenge remains around their tendency to hallucinate generating content that appears factual but ... [Jan 2024] (Citations: 465; Topics: Hallucination in LLMs, LLM Overview & History)
Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model📑: We introduce Open-Reasoner-Zero, the first open source implementation of large-scale reasoning-oriented RL training on the base model focusing on scalability, simplicity and accessibility. [Mar 2025] (Citations: 464; Topics: Reasoning in LLMs, RLVR & Process Reward Models, Inference-Time Scaling & Test-Time Compute)
Understanding the planning of LLM agents: A survey📑: As Large Language Models (LLMs) have shown significant intelligence, the progress to leverage LLMs as planning modules of autonomous agents has attracted more attention. [Feb 2024] (Citations: 463; Topics: LLM Agents, LLM Architecture Innovations, LLM Overview & History)
A Survey on Model Compression for Large Language Models📑: Abstract Large Language Models (LLMs) have transformed natural language processing tasks successfully. [Aug 2023] (Citations: 462; Topics: Efficient LLMs: Training & Inference, LLM Overview & History)
Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models📑: Proprietary LMs such as GPT-4 are often employed to assess the quality of responses from various LMs. [May 2024] (Citations: 455; Topics: LLM Overview & History)
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models📑: Large language models (LLMs) have revolutionized natural language processing tasks. [Aug 2023] (Citations: 451; Topics: Efficient LLMs: Training & Inference)
Graph Retrieval-Augmented Generation: A Survey📑: Recently, Retrieval-Augmented Generation (RAG) has achieved remarkable success in addressing the challenges of Large Language Models (LLMs) without necessitating retraining. [Aug 2024] (Citations: 450; Topics: Retrieval-Augmented Generation (RAG), GraphRAG & Knowledge Graphs, LLM Overview & History)
Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision📑: Recent AI-assistant agents, such as ChatGPT, predominantly rely on supervised fine-tuning (SFT) with human annotations and reinforcement learning from human feedback (RLHF) to align the output of ... [May 2023] (Citations: 449; Topics: Alignment & RLHF, LLM Agents, RLAIF & Constitutional AI)
SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Task Planning📑: Large language models (LLMs) have demonstrated impressive results in developing generalist planning agents for diverse tasks. [Jul 2023] (Citations: 445; Topics: LLM Agents, LLM for Robotics & Embodied AI, GraphRAG & Knowledge Graphs)
On the Planning Abilities of Large Language Models - A Critical Investigation📑: Intrigued by the claims of emergent reasoning capabilities in LLMs trained on general web corpora, in this paper, we set out to investigate their planning capabilities. [May 2023] (Citations: 445; Topics: Reasoning in LLMs, LLM Agents, Scaling Laws)
LLMRec: Large Language Models with Graph Augmentation for Recommendation📑: The problem of data sparsity has long been a challenge in recommendation systems, and previous studies have attempted to address this issue by incorporating side information. [Nov 2023] (Citations: 442; Topics: Data for LLMs, GraphRAG & Knowledge Graphs)
Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory📑: Large Language Models (LLMs) have demonstrated remarkable prowess in generating contextually coherent responses, yet their fixed context windows pose fundamental challenges for maintaining ... [Apr 2025] (Citations: 441; Topics: LLM Memory & Personalization, LLM Agents, Context Engineering)
RewardBench: Evaluating Reward Models for Language Modeling📑: Reward models (RMs) are at the crux of successfully using RLHF to align pretrained models to human preferences, yet there has been relatively little study that focuses on evaluation of those models. [Mar 2024] (Citations: 438; Topics: Alignment & RLHF, Evaluation of LLMs & Agents, RLAIF & Constitutional AI)
MM-LLMs: Recent Advances in MultiModal Large Language Models📑: In the past year, MultiModal Large Language Models (MM-LLMs) have undergone substantial advancements, augmenting off-the-shelf LLMs to support MM inputs or outputs via cost-effective training ... [Jan 2024] (Citations: 436; Topics: Multimodal LLMs)
Mixture-of-Agents Enhances Large Language Model Capabilities📑: Recent advances in large language models (LLMs) demonstrate substantial capabilities in natural language understanding and generation tasks. [Jun 2024] (Citations: 435; Topics: LLM Agents, Hallucination in LLMs)
Search-o1: Agentic Search-Enhanced Large Reasoning Models📑: Large reasoning models (LRMs) like OpenAI-o1 have demonstrated impressive long stepwise reasoning capabilities through large-scale reinforcement learning. [Jan 2025] (Citations: 433; Topics: Reasoning in LLMs, LLM Agents, RLVR & Process Reward Models)
Towards Measuring the Representation of Subjective Global Opinions in Language Models📑: Large language models (LLMs) may not equitably represent diverse global perspectives on societal issues. [Jun 2023] (Citations: 432; Topics: LLM Overview & History)
Self-Supervised Learning for Recommender Systems: A Survey📑: In recent years, neural architecture-based recommender systems have achieved tremendous success, but they still fall short of expectation when dealing with highly sparse data. [Mar 2022] (Citations: 428; Topics: Self-Supervised & Representation Learning, Data for LLMs, LLM Overview & History)
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models📑: Without proper safeguards, large language models will readily follow malicious instructions and generate toxic content. [Aug 2023] (Citations: 427; Topics: Trustworthy & Secure LLMs, Instruction Tuning & SFT)
QuIP: 2-Bit Quantization of Large Language Models With Guarantees📑: This work studies post-training parameter quantization in large language models (LLMs). [Jul 2023] (Citations: 424; Topics: Efficient LLMs: Training & Inference, Alignment & RLHF)
Video-R1: Reinforcing Video Reasoning in MLLMs📑: Inspired by DeepSeek-R1's success in eliciting reasoning abilities through rule-based reinforcement learning (RL), we introduce Video-R1 as the first attempt to systematically explore the R1 paradigm ... [Mar 2025] (Citations: 423; Topics: Reasoning in LLMs, RLVR & Process Reward Models, Multimodal LLMs)
LocalMamba: Visual State Space Model with Windowed Selective Scan📑: Recent advancements in state space models, notably Mamba, have demonstrated significant progress in modeling long sequences for tasks like language understanding. [Mar 2024] (Citations: 422; Topics: LLM Architecture Innovations)
SpinQuant: LLM quantization with learned rotations📑: Post-training quantization (PTQ) techniques applied to weights, activations, and the KV cache greatly reduce memory usage, latency, and power consumption of Large Language Models (LLMs), but may lead ... [May 2024] (Citations: 421; Topics: LLM Architecture Innovations, Efficient LLMs: Training & Inference, LLM Memory & Personalization)
The Lessons of Developing Process Reward Models in Mathematical Reasoning📑: Process Reward Models (PRMs) emerge as a promising approach for process supervision in mathematical reasoning of Large Language Models (LLMs), which aim to identify and mitigate intermediate errors ... [Jan 2025] (Citations: 416; Topics: Reasoning in LLMs, RLVR & Process Reward Models, Alignment & RLHF)
ST-MoE: Designing Stable and Transferable Sparse Expert Models📑: Scale has opened new frontiers in natural language processing -- but at a high cost. [Feb 2022] (Citations: 415; Topics: Mixture of Experts, Tabular Data & NL2SQL)
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits📑: Recent research, such as BitNet, is paving the way for a new era of 1-bit Large Language Models (LLMs). [Feb 2024] (Citations: 414; Topics: LLM Overview & History)
Fine-Tuning Language Models with Just Forward Passes📑: Fine-tuning language models (LMs) has yielded success on diverse downstream tasks, but as LMs grow in size, backpropagation requires a prohibitively large amount of memory. [May 2023] (Citations: 414; Topics: LLM Memory & Personalization, PEFT & LoRA, Instruction Tuning & SFT)
Hallucination of Multimodal Large Language Models: A Survey📑: This survey presents a comprehensive analysis of the phenomenon of hallucination in multimodal large language models (MLLMs), also known as Large Vision-Language Models (LVLMs), which have ... [Apr 2024] (Citations: 413; Topics: Multimodal LLMs, Hallucination in LLMs, LLM Overview & History)
Improve Mathematical Reasoning in Language Models by Automated Process Supervision📑: Complex multi-step reasoning tasks, such as solving mathematical problems or generating code, remain a significant hurdle for even the most advanced large language models (LLMs). [Jun 2024] (Citations: 412; Topics: Reasoning in LLMs, LLMs for Code, RLVR & Process Reward Models)
TravelPlanner: A Benchmark for Real-World Planning with Language Agents📑: Planning has been part of the core pursuit for artificial intelligence since its conception, but earlier AI agents mostly focused on constrained settings because many of the cognitive substrates ... [Feb 2024] (Citations: 412; Topics: LLM Agents, Evaluation of LLMs & Agents, Federated & Personalized AI)
Large Language Models are Better Reasoners with Self-Verification📑: Recently, with the chain of thought (CoT) prompting, large language models (LLMs), e. [Dec 2022] (Citations: 411; Topics: Reasoning in LLMs, Prompt Engineering & In-Context Learning, Inference-Time Scaling & Test-Time Compute)
ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning📑: Over the last few years, large language models (LLMs) have emerged as the most important breakthroughs in natural language processing (NLP) that fundamentally transform research and developments in ... [Apr 2023] (Citations: 410; Topics: Evaluation of LLMs & Agents, LLM Overview & History)
A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems📑: With the widespread adoption of deep learning, reinforcement learning (RL) has experienced a dramatic increase in popularity, scaling to previously intractable problems, such as playing complex games ... [Mar 2022] (Citations: 410; Topics: RLVR & Process Reward Models, Tabular Data & NL2SQL, LLM Overview & History)
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models📑: Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks. [Mar 2025] (Citations: 409; Topics: Reasoning in LLMs, Inference-Time Scaling & Test-Time Compute, Efficient LLMs: Training & Inference)
A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4📑: Large language models (LLMs) are a special class of pretrained language models obtained by scaling model size, pretraining corpus and computation. [Oct 2023] (Citations: 407; Topics: LLM Overview & History, Scaling Laws)
NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models📑: Trained with an unprecedented scale of data, large language models (LLMs) like ChatGPT and GPT-4 exhibit the emergence of significant reasoning abilities from model scaling. [May 2023] (Citations: 404; Topics: LLM Overview & History, Reasoning in LLMs, Scaling Laws)
Vision-Language Foundation Models as Effective Robot Imitators📑: Recent progress in vision language foundation models has shown their ability to understand multimodal data and resolve complicated vision language tasks, including robotics manipulation. [Nov 2023] (Citations: 404; Topics: Multimodal LLMs, LLM for Robotics & Embodied AI, LLM Overview & History)
SliceGPT: Compress Large Language Models by Deleting Rows and Columns📑: Large language models have become the cornerstone of natural language processing, but their use comes with substantial costs in terms of compute and memory resources. [Jan 2024] (Citations: 401; Topics: LLM Memory & Personalization)
Continual learning of context-dependent processing in neural networks📑: Deep neural networks are powerful tools in learning sophisticated but fixed mapping rules between inputs and outputs, thereby limiting their application in more complex and dynamic situations in ... [Oct 2018] (Citations: 400; Topics: Continual Learning & Model Merging, Function Calling & Tool Use, Prompt Engineering & In-Context Learning)
Multimodal Large Language Models: A Survey📑: The exploration of multimodal language models integrates multiple data types, such as images, text, language, audio, and other heterogeneity. [Nov 2023] (Citations: 398; Topics: Multimodal LLMs, Data for LLMs, LLM Overview & History)
Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning📑: We consider the problem of model compression for deep neural networks (DNNs) in the challenging one-shot/post-training setting, in which we are given an accurate trained model, and must compress it ... [Aug 2022] (Citations: 397; Topics: Efficient LLMs: Training & Inference, Scaling Laws, Alignment & RLHF)
Dataless Knowledge Fusion by Merging Weights of Language Models📑: Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. [Dec 2022] (Citations: 397; Topics: Continual Learning & Model Merging, PEFT & LoRA, Instruction Tuning & SFT)
A Cookbook of Self-Supervised Learning📑: Self-supervised learning, dubbed the dark matter of intelligence, is a promising path to advance machine learning. [Apr 2023] (Citations: 396; Topics: Self-Supervised & Representation Learning, Instruction Tuning & SFT)
What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning📑: Instruction tuning is a standard technique employed to align large language models to end tasks and user preferences after the initial pretraining phase. [Dec 2023] (Citations: 396; Topics: Instruction Tuning & SFT, Alignment & RLHF, LLM Memory & Personalization)
VerilogEval: Evaluating Large Language Models for Verilog Code Generation📑: The increasing popularity of large language models (LLMs) has paved the way for their application in diverse domains. [Sep 2023] (Citations: 396; Topics: LLMs for Code)
Understanding the Effects of RLHF on LLM Generalisation and Diversity📑: Large language models (LLMs) fine-tuned with reinforcement learning from human feedback (RLHF) have been used in some of the most widely deployed AI models to date, such as OpenAI's ChatGPT or ... [Oct 2023] (Citations: 396; Topics: Alignment & RLHF, RLVR & Process Reward Models, LLM Overview & History)
Dream 7B: Diffusion Large Language Models📑: We introduce Dream 7B, the most powerful open diffusion large language model to date. [Aug 2025] (Citations: 393; Topics: LLM Overview & History)
Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval📑: Recent research demonstrates the effectiveness of using fine-tuned language models (LM) for dense retrieval. [Aug 2021] (Citations: 390; Topics: Embeddings & Vector Search, Retrieval-Augmented Generation (RAG), Instruction Tuning & SFT)
Leveraging large language models for predictive chemistry📑: Machine learning has transformed many fields and has recently found applications in chemistry and materials science. (Citations: 390; Topics: LLMs for Healthcare & Science)
Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts📑: Reinforcement learning from human feedback (RLHF) has emerged as the primary method for aligning large language models (LLMs) with human preferences. [Jun 2024] (Citations: 390; Topics: Alignment & RLHF, Mixture of Experts, RLAIF & Constitutional AI)
How Can Recommender Systems Benefit from Large Language Models: A Survey📑: With the rapid development of online services and web applications, recommender systems (RS) have become increasingly indispensable for mitigating information overload and matching users’ information ... [Jun 2023] (Citations: 388; Topics: LLM Overview & History)
Foundation models in robotics: Applications, challenges, and the future📑: We survey applications of pretrained foundation models in robotics. [Dec 2023] (Citations: 388; Topics: LLM Overview & History, LLM for Robotics & Embodied AI, LLMs for Code)
Agent Laboratory: Using LLM Agents as Research Assistants📑: Historically, scientific discovery has been a lengthy and costly process, demanding substantial time and resources from initial conception to final results. [Jan 2025] (Citations: 387; Topics: LLM Agents, LLMs for Healthcare & Science, Inference-Time Scaling & Test-Time Compute)
Improving Text Embeddings with Large Language Models📑: In this paper, we introduce a novel and simple method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps. [Jan 2024] (Citations: 386; Topics: Data for LLMs, Embeddings & Vector Search, Instruction Tuning & SFT)
Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters📑: Chain-of-Thought (CoT) prompting can dramatically improve the multi-step reasoning abilities of large language models (LLMs). [Dec 2022] (Citations: 385; Topics: Reasoning in LLMs, Prompt Engineering & In-Context Learning, Inference-Time Scaling & Test-Time Compute)
DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models📑: Despite their impressive capabilities, large language models (LLMs) are prone to hallucinations, i. [Sep 2023] (Citations: 385; Topics: Hallucination in LLMs)
VeriGen: A Large Language Model for Verilog Code Generation📑: In this study, we explore the capability of Large Language Models (LLMs) to automate hardware design by automatically completing partial Verilog code, a common language for designing and modeling ... [Aug 2023] (Citations: 385; Topics: LLMs for Code)
Agentless: Demystifying LLM-based Software Engineering Agents📑: Recent advancements in large language models (LLMs) have significantly advanced the automation of software development tasks, including code synthesis, program repair, and test generation. [Jul 2024] (Citations: 385; Topics: LLMs for Code, LLM Agents, GUI Agents)
AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning📑: Fine-tuning large pre-trained language models on downstream tasks has become an important paradigm in NLP. [Mar 2023] (Citations: 384; Topics: PEFT & LoRA, Efficient LLMs: Training & Inference, Instruction Tuning & SFT)
CAMEL: Communicative Agents for "Mind" Exploration of Large Scale Language Model Society📑 (Citations: 383; Topics: LLM Agents)
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models📑: Several post-training quantization methods have been applied to large language models (LLMs), and have been shown to perform well down to 8-bits. [May 2023] (Citations: 383; Topics: Efficient LLMs: Training & Inference, Data for LLMs, Alignment & RLHF)
CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models📑: In our previous work, we introduced CosyVoice, a multilingual speech synthesis model based on supervised discrete speech tokens. [Dec 2024] (Citations: 383; Topics: LLM Overview & History)
Visual Adversarial Examples Jailbreak Aligned Large Language Models📑: Warning: this paper contains data, prompts, and model outputs that are offensive in nature. [Jun 2023] (Citations: 383; Topics: Trustworthy & Secure LLMs, Prompt Engineering & In-Context Learning, Data for LLMs)
Scaling LLM Test-Time Compute Optimally Can be More Effective than Scaling Parameters for Reasoning📑 (Citations: 380; Topics: Inference-Time Scaling & Test-Time Compute, Reasoning in LLMs, Scaling Laws)
FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation📑: Most large language models (LLMs) are trained once and never updated; thus, they lack the ability to dynamically adapt to our ever-changing world. [Oct 2023] (Citations: 378; Topics: LLM Overview & History)
CERT: Contrastive Self-supervised Learning for Language Understanding📑: Pretrained language models such as BERT, GPT have shown great effectiveness in language understanding. [May 2020] (Citations: 377; Topics: Self-Supervised & Representation Learning, Instruction Tuning & SFT)
Preference Ranking Optimization for Human Alignment📑: Large language models (LLMs) often contain misleading content, emphasizing the need to align them with human values to ensure secure AI systems. [Jun 2023] (Citations: 377; Topics: Alignment & RLHF)
Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint📑: This paper studies the alignment process of generative models with Reinforcement Learning from Human Feedback (RLHF). [Dec 2023] (Citations: 377; Topics: Alignment & RLHF, RLAIF & Constitutional AI, RLVR & Process Reward Models)
ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases📑: Enabling large language models to utilize real-world tools effectively is crucial for achieving embodied intelligence. [Jun 2023] (Citations: 376; Topics: Function Calling & Tool Use, LLM for Robotics & Embodied AI, Instruction Tuning & SFT)
SpecInfer: Accelerating Large Language Model Serving with Tree-based Speculative Inference and Verification📑: This paper introduces SpecInfer, a system that accelerates generative large language model (LLM) serving with tree-based speculative inference and verification. [May 2023] (Citations: 376; Topics: Efficient LLMs: Training & Inference, LLMOps & Model Serving)
Process Reinforcement through Implicit Rewards📑: Dense process rewards have proven a more effective alternative to the sparse outcome-level rewards in the inference-time scaling of large language models (LLMs), particularly in tasks requiring ... [Feb 2025] (Citations: 372; Topics: RLVR & Process Reward Models, Inference-Time Scaling & Test-Time Compute, Reasoning in LLMs)
RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback📑 (Citations: 371; Topics: RLAIF & Constitutional AI, Alignment & RLHF, RLVR & Process Reward Models)
Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Services📑: Artificial Intelligence-Generated Content (AIGC) is an automated method for generating, manipulating, and modifying valuable and diverse data using AI algorithms creatively. [Mar 2023] (Citations: 369; Topics: LLM Overview & History, Data for LLMs, Federated & Personalized AI)
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models📑: We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that supports both ... [Aug 2025] (Citations: 368; Topics: Mixture of Experts, LLM Overview & History, LLM Agents)
TinyVLA: Toward Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation📑: Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes. [Sep 2024] (Citations: 367; Topics: LLM for Robotics & Embodied AI, Multimodal LLMs, Efficient LLMs: Training & Inference)
SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics📑: Vision-language models (VLMs) pretrained on large-scale multimodal datasets encode rich visual and linguistic knowledge, making them a strong foundation for robotics. [Jun 2025] (Citations: 367; Topics: LLM for Robotics & Embodied AI, Multimodal LLMs, Efficient LLMs: Training & Inference)
From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning📑: In the realm of Large Language Models (LLMs), the balance between instruction data quality and quantity is a focal point. [Aug 2023] (Citations: 365; Topics: Instruction Tuning & SFT, Data for LLMs, Scaling Laws)
A Survey on Hallucination in Large Vision-Language Models📑: Recent development of Large Vision-Language Models (LVLMs) has attracted growing attention within the AI landscape for its practical implementation potential. [Feb 2024] (Citations: 364; Topics: Multimodal LLMs, LLM Architecture Innovations, Hallucination in LLMs)
∞Bench: Extending Long Context Evaluation Beyond 100K Tokens📑: Processing and reasoning over long contexts is crucial for many practical applications of Large Language Models (LLMs), such as document comprehension and agent construction. [Feb 2024] (Citations: 364; Topics: Context Engineering, Evaluation of LLMs & Agents, Reasoning in LLMs)
Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach📑: In the past few decades, recommender systems have attracted much attention in both research and industry communities. [May 2023] (Citations: 362; Topics: Instruction Tuning & SFT, LLM Architecture Innovations, Efficient LLMs: Training & Inference)
The General Attitudes towards Artificial Intelligence Scale (GAAIS): Confirmatory Validation and Associations with Personality, Corporate Distrust, and General Trust📑: Abstract Acceptance of Artificial Intelligence (AI) may be predicted by individual psychological correlates, examined here. (Citations: 362; Topics: Federated & Personalized AI)
AI and Memory Wall📑: The availability of unprecedented unsupervised training data, along with neural scaling laws, has resulted in an unprecedented surge in model size and compute requirements for serving/training large ... [Mar 2024] (Citations: 362; Topics: Scaling Laws, LLM Memory & Personalization, Efficient LLMs: Training & Inference)
ShortGPT: Layers in Large Language Models are More Redundant Than You Expect📑: As Large Language Models (LLMs) continue to advance in performance, their size has escalated significantly, with current LLMs containing billions or even trillions of parameters. [Mar 2024] (Citations: 361; Topics: Scaling Laws)
Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents📑: Multimodal large language models (MLLMs) are transforming the capabilities of graphical user interface (GUI) agents, facilitating their transition from controlled simulations to complex, real-world ... [Oct 2024] (Citations: 360; Topics: GUI Agents, LLM Agents, Multimodal LLMs)
GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest📑: Visual instruction tuning large language model(LLM) on image-text pairs has achieved general-purpose vision-language abilities. [Jul 2023] (Citations: 359; Topics: Instruction Tuning & SFT, Multimodal LLMs, PEFT & LoRA)
Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment📑: With the continuous growth in the number of parameters of the Transformer-based pretrained language models (PLMs), particularly the emergence of large language models (LLMs) with billions of ... [Dec 2023] (Citations: 354; Topics: PEFT & LoRA, Efficient LLMs: Training & Inference, Instruction Tuning & SFT)
RSMamba: Remote Sensing Image Classification With State Space Model📑: Remote sensing image classification forms the foundation of various understanding tasks, serving a crucial function in remote sensing image interpretation. [Mar 2024] (Citations: 354; Topics: LLM Architecture Innovations, Multimodal LLMs, Efficient LLMs: Training & Inference)
The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models📑 (Citations: 354; Topics: Function Calling & Tool Use, Evaluation of LLMs & Agents, LLM Agents)
QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks📑: Post-training quantization (PTQ) reduces the memory footprint of LLMs by quantizing their weights to low-precision. [Feb 2024] (Citations: 353; Topics: Efficient LLMs: Training & Inference, LLM Memory & Personalization, Alignment & RLHF)
Improving large language models for clinical named entity recognition via prompt engineering📑: Abstract Importance The study highlights the potential of large language models, specifically GPT-3. (Citations: 352; Topics: Prompt Engineering & In-Context Learning, LLMs for Healthcare & Science)
Foundation Models Defining a New Era in Vision: A Survey and Outlook📑: Vision systems that see and reason about the compositional nature of visual scenes are fundamental to understanding our world. (Citations: 352; Topics: LLM Overview & History, Multimodal LLMs)
TrustLLM: Trustworthiness in Large Language Models📑: Large language models (LLMs), exemplified by ChatGPT, have gained considerable attention for their excellent natural language processing capabilities. [Jan 2024] (Citations: 349; Topics: LLM Architecture Innovations, LLM Overview & History, Efficient LLMs: Training & Inference)
ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback📑: Learning from human feedback has become a pivot technique in aligning large language models (LLMs) with human preferences. [Oct 2023] (Citations: 347; Topics: Alignment & RLHF, RLAIF & Constitutional AI)
Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge📑: LLM-as-a-Judge has been widely utilized as an evaluation method in various benchmarks and served as supervised rewards in model training. [Oct 2024] (Citations: 345; Topics: Evaluation of LLMs & Agents, LLM Agents, Instruction Tuning & SFT)
MoE-LLaVA: Mixture of Experts for Large Vision-Language Models📑: Recently, remarkable progress has been made in scaling up Large Language Models (LLMs) through the use of the sparse Mixture-of-Expert (MoE) layers without significantly increasing computational cost. [Jan 2024] (Citations: 344; Topics: Mixture of Experts, Multimodal LLMs, Scaling Laws)
A Survey on Knowledge Distillation of Large Language Models📑: In the era of Large Language Models (LLMs), Knowledge Distillation (KD) emerges as a pivotal methodology for transferring advanced capabilities from leading proprietary LLMs, such as GPT-4, to their ... [Feb 2024] (Citations: 344; Topics: Efficient LLMs: Training & Inference, LLM Overview & History)
Large Language Models for Education: A survey and outlook📑: The advent of large language models (LLMs) has ushered in a new era of possibilities in the realm of education. [Mar 2024] (Citations: 343; Topics: LLM Overview & History)
Analyzing and Mitigating Object Hallucination in Large Vision-Language Models📑: Large vision-language models (LVLMs) have shown remarkable abilities in understanding visual information with human languages. [Oct 2023] (Citations: 340; Topics: Multimodal LLMs, Hallucination in LLMs)
L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning📑: Reasoning language models have shown an uncanny ability to improve performance at test-time by ``thinking longer''-that is, by generating longer chain-of-thought sequences and hence using more ... [Mar 2025] (Citations: 340; Topics: Inference-Time Scaling & Test-Time Compute, Reasoning in LLMs, RLVR & Process Reward Models)
Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory📑: The captivating realm of Minecraft has attracted substantial research interest in recent years, serving as a rich platform for developing intelligent agents capable of functioning in open-world ... [May 2023] (Citations: 339; Topics: LLM Agents, LLM Memory & Personalization, Efficient LLMs: Training & Inference)
Structured Chain-of-Thought Prompting for Code Generation📑: Large Language Models (LLMs) have shown impressive abilities in code generation. [May 2023] (Citations: 339; Topics: LLMs for Code, Reasoning in LLMs, Prompt Engineering & In-Context Learning)
The rise and potential of large language model based agents: a survey📑 (Citations: 339; Topics: LLM Agents, LLM Overview & History)
Large Language Models for Mathematical Reasoning: Progresses and Challenges📑: Mathematical reasoning serves as a cornerstone for assessing the fundamental cognitive capabilities of human intelligence. [Feb 2024] (Citations: 338; Topics: Reasoning in LLMs, Multimodal LLMs)
VideoAgent: Long-form Video Understanding with Large Language Model as Agent📑: Long-form video understanding represents a significant challenge within computer vision, demanding a model capable of reasoning over long multi-modal sequences. [Mar 2024] (Citations: 338; Topics: Multimodal LLMs, Reasoning in LLMs, LLM Agents)
A Survey on Mixture of Experts in Large Language Models📑: Large language models (LLMs) have garnered unprecedented advancements across diverse fields, ranging from natural language processing to computer vision and beyond. [Jul 2024] (Citations: 335; Topics: Mixture of Experts, LLM Overview & History)
OpenEQA: Embodied Question Answering in the Era of Foundation Models📑 (Citations: 333; Topics: LLM Overview & History, LLM for Robotics & Embodied AI, Tabular Data & NL2SQL)
OpenChat: Advancing Open-source Language Models with Mixed-Quality Data📑: Nowadays, open-source large language models like LLaMA have emerged. [Sep 2023] (Citations: 332; Topics: Data for LLMs, LLM Overview & History)
Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG📑: Large Language Models (LLMs) have advanced artificial intelligence by enabling human-like text generation and natural language understanding. [Jan 2025] (Citations: 332; Topics: Retrieval-Augmented Generation (RAG), LLM Agents, LLM Overview & History)
Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning📑: Multi-Modal Large Language Models (MLLMs) have demonstrated impressive performance in various VQA tasks. [Mar 2024] (Citations: 332; Topics: Reasoning in LLMs, Evaluation of LLMs & Agents, Data for LLMs)
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking📑: We present rStar-Math to demonstrate that small language models (SLMs) can rival or even surpass the math reasoning capability of OpenAI o1, without distillation from superior models. [Jan 2025] (Citations: 331; Topics: Reasoning in LLMs, Small Language Models, Inference-Time Scaling & Test-Time Compute)
Humans or LLMs as the Judge? A Study on Judgement Bias📑: Adopting human and large language models (LLM) as judges (*a. [Feb 2024] (Citations: 331; Topics: Evaluation of LLMs & Agents)
Large Language Model Guided Tree-of-Thought📑: In this paper, we introduce the Tree-of-Thought (ToT) framework, a novel approach aimed at improving the problem-solving capabilities of auto-regressive large language models (LLMs). [May 2023] (Citations: 330; Topics: Reasoning in LLMs, RLVR & Process Reward Models)
SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation📑: The rapid evolution of multimodal foundation model has demonstrated significant progresses in vision-language understanding and generation, e. [Apr 2024] (Citations: 330; Topics: Multimodal LLMs, Evaluation of LLMs & Agents)
From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference📑: Large language models (LLMs) have exploded in popularity due to their new generative capabilities that go far beyond prior state-of-the-art. [Oct 2023] (Citations: 328; Topics: Evaluation of LLMs & Agents, Efficient LLMs: Training & Inference)
Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols📑: Learning to communicate through interaction, rather than relying on explicit supervision, is often considered a prerequisite for developing a general AI. [May 2017] (Citations: 327; Topics: LLM Agents, Multimodal LLMs)
Atom: Low-bit Quantization for Efficient and Accurate LLM Serving📑: The growing demand for Large Language Models (LLMs) in applications such as content generation, intelligent chatbots, and sentiment analysis poses considerable challenges for LLM service providers. [Oct 2023] (Citations: 327; Topics: Efficient LLMs: Training & Inference, LLMOps & Model Serving, LLM Overview & History)
Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models📑: Recent advancements in reasoning with large language models (RLLMs), such as OpenAI-O1 and DeepSeek-R1, have demonstrated their impressive capabilities in complex domains like mathematics and coding. [Mar 2025] (Citations: 326; Topics: Reasoning in LLMs, LLM Overview & History, Inference-Time Scaling & Test-Time Compute)
OS-ATLAS: A Foundation Action Model for Generalist GUI Agents📑: Existing efforts in building GUI agents heavily rely on the availability of robust commercial Vision-Language Models (VLMs) such as GPT-4o and GeminiProVision. [Oct 2024] (Citations: 326; Topics: GUI Agents, LLM Agents, Multimodal LLMs)
MegaScale: Scaling Large Language Model Training to More Than 10, 000 GPUs📑: We present the design, implementation and engineering experience in building and deploying MegaScale, a production system for training large language models (LLMs) at the scale of more than 10,000 ... [Feb 2024] (Citations: 325; Topics: LLM Overview & History)
Scaling Laws for Transfer📑: We study empirical scaling laws for transfer learning between distributions in an unsupervised, fine-tuning setting. [Feb 2021] (Citations: 325; Topics: Scaling Laws, PEFT & LoRA, Instruction Tuning & SFT)
GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction📑: This paper aims to efficiently enable Large Language Models (LLMs) to use multimodal tools. [May 2023] (Citations: 325; Topics: Instruction Tuning & SFT, Multimodal LLMs, Efficient LLMs: Training & Inference)
Evaluating Large Language Models at Evaluating Instruction Following📑: As research in large language models (LLMs) continues to accelerate, LLM-based evaluation has emerged as a scalable and cost-effective alternative to human evaluations for comparing the ever ... [Oct 2023] (Citations: 325; Topics: Instruction Tuning & SFT, Evaluation of LLMs & Agents)
Break the Sequential Dependency of LLM Inference Using Lookahead Decoding📑: Autoregressive decoding of large language models (LLMs) is memory bandwidth bounded, resulting in high latency and significant wastes of the parallel processing power of modern accelerators. [Feb 2024] (Citations: 324; Topics: Efficient LLMs: Training & Inference, LLM Memory & Personalization)
Towards artificial general intelligence via a multimodal foundation model📑: The fundamental goal of artificial intelligence (AI) is to mimic the core cognitive activities of human. [Oct 2021] (Citations: 321; Topics: Multimodal LLMs, Federated & Personalized AI)
Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection📑: Recent studies in deepfake detection have yielded promising results when the training and testing face forgeries are from the same dataset. [Mar 2022] (Citations: 321; Topics: Self-Supervised & Representation Learning, Data for LLMs, Trustworthy & Secure LLMs)
S3: Social-network Simulation System with Large Language Model-Empowered Agents📑: Social network simulation plays a crucial role in addressing various challenges within social science. [Jul 2023] (Citations: 321; Topics: LLM Agents, LLMs for Healthcare & Science)
Measuring short-form factuality in large language models📑: We present SimpleQA, a benchmark that evaluates the ability of language models to answer short, fact-seeking questions. [Nov 2024] (Citations: 319; Topics: Evaluation of LLMs & Agents, Hallucination in LLMs)
The ethics of ChatGPT in medicine and healthcare: a systematic review on Large Language Models (LLMs)📑: With the introduction of ChatGPT, Large Language Models (LLMs) have received enormous attention in healthcare. [Mar 2024] (Citations: 318; Topics: LLMs for Healthcare & Science, LLM Architecture Innovations, LLM Overview & History)
Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models📑: Warning: This paper contains examples of harmful language, and reader discretion is recommended. [Oct 2023] (Citations: 317; Topics: Alignment & RLHF)
ReTool: Reinforcement Learning for Strategic Tool Use in LLMs📑: While reasoning models (e.g., DeepSeek R1) trained with reinforcement learning (RL), excel in textual reasoning, they struggle in scenarios requiring structured problem-solving, such as geometric ... [Apr 2025] (Citations: 316; Topics: Reasoning in LLMs, Function Calling & Tool Use, RLVR & Process Reward Models)
Evaluating Large Language Models: A Comprehensive Survey📑: Large language models (LLMs) have demonstrated remarkable capabilities across a broad spectrum of tasks. [Oct 2023] (Citations: 315; Topics: LLM Overview & History)
Leveraging Large Language Models for Mental Health Prediction via Online Text Data📑 (Citations: 313; Topics: Data for LLMs)
Dense Text Retrieval Based on Pretrained Language Models: A Survey📑: Text retrieval is a long-standing research topic on information seeking, where a system is required to return relevant information resources to user’s queries in natural language. [Nov 2022] (Citations: 312; Topics: Embeddings & Vector Search, LLM Overview & History, Retrieval-Augmented Generation (RAG))
Building Cooperative Embodied Agents Modularly with Large Language Models📑: In this work, we address challenging multi-agent cooperation problems with decentralized control, raw sensory observations, costly communication, and multi-objective tasks instantiated in various ... [Jul 2023] (Citations: 311; Topics: LLM Agents, LLM for Robotics & Embodied AI)
R1-VL: Learning to Reason with Multimodal Large Language Models via Step-Wise Group Relative Policy Optimization📑: Recent studies generally enhance MLLMs' reasoning capabilities via supervised fine-tuning on high-quality chain-of-thought reasoning data, which often leads models to merely imitate successful ... [Mar 2025] (Citations: 311; Topics: Reasoning in LLMs, Multimodal LLMs, Instruction Tuning & SFT)
PointMamba: A Simple State Space Model for Point Cloud Analysis📑: Transformers have become one of the foundational architectures in point cloud analysis tasks due to their excellent global modeling ability. [Feb 2024] (Citations: 311; Topics: LLM Architecture Innovations)
HealthBench: Evaluating Large Language Models Towards Improved Human Health📑: We present HealthBench, an open-source benchmark measuring the performance and safety of large language models in healthcare. [May 2025] (Citations: 311; Topics: Evaluation of LLMs & Agents, LLMs for Healthcare & Science, Trustworthy & Secure LLMs)
A framework to assess clinical safety and hallucination rates of LLMs for medical text summarisation📑: Integrating large language models (LLMs) into healthcare can enhance workflow efficiency and patient care by automating tasks such as summarising consultations. (Citations: 310; Topics: LLMs for Healthcare & Science, Hallucination in LLMs, Trustworthy & Secure LLMs)
ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning for Action Recognition📑: Capitalizing on large pre-trained models for various downstream tasks of interest have recently emerged with promising performance. [Jun 2022] (Citations: 308; Topics: PEFT & LoRA, Multimodal LLMs, Efficient LLMs: Training & Inference)
Evaluating word embedding models: methods and experimental results📑: Abstract Extensive evaluation on a large number of word embedding models for language processing applications is conducted in this work. [Jan 2019] (Citations: 307; Topics: Evaluation of LLMs & Agents, Embeddings & Vector Search)
On the Challenges and Perspectives of Foundation Models for Medical Image Analysis📑: This article discusses the opportunities, applications and future directions of large-scale pretrained models, i. [Jun 2023] (Citations: 307; Topics: LLM Overview & History, Multimodal LLMs, LLMs for Healthcare & Science)
Large Language Models as Tool Makers📑: Recent research has highlighted the potential of large language models (LLMs) to improve their problem-solving capabilities with the aid of suitable external tools. [May 2023] (Citations: 307; Topics: Function Calling & Tool Use, Tabular Data & NL2SQL, Reasoning in LLMs)
How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition📑: Large language models (LLMs) with enormous pre-training tokens and parameters emerge diverse abilities, including math reasoning, code generation, and instruction following. [Oct 2023] (Citations: 307; Topics: Instruction Tuning & SFT, LLMs for Code, Reasoning in LLMs)
CodeS: Towards Building Open-source Language Models for Text-to-SQL📑: Language models have shown promising performance on the task of translating natural language questions into SQL queries (Text-to-SQL). [Feb 2024] (Citations: 306; Topics: Tabular Data & NL2SQL, LLM Overview & History, Retrieval-Augmented Generation (RAG))
Orthogonal Subspace Learning for Language Model Continual Learning📑: Benefiting from massive corpora and advanced hardware, large language models (LLMs) exhibit remarkable capabilities in language understanding and generation. [Oct 2023] (Citations: 305; Topics: Continual Learning & Model Merging)
Large Language Models for Data Annotation and Synthesis: A Survey📑: Data annotation and synthesis generally refers to the labeling or generating of raw data with relevant information, which could be used for improving the efficacy of machine learning models. [Feb 2024] (Citations: 304; Topics: Data for LLMs, LLM Overview & History)
Rethinking machine unlearning for large language models📑: We explore machine unlearning in the domain of large language models (LLMs), referred to as LLM unlearning. [Feb 2024] (Citations: 302; Topics: Inference-Time Scaling & Test-Time Compute, RLVR & Process Reward Models)
VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning📑: Recently, slow-thinking systems like GPT-o1 and DeepSeek-R1 have demonstrated great potential in solving challenging problems through explicit reflection. [Apr 2025] (Citations: 302; Topics: Multimodal LLMs, RLVR & Process Reward Models, Reasoning in LLMs)
Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction📑: Robust prediction of citywide traffic flows at different time periods plays a crucial role in intelligent transportation systems. [Dec 2022] (Citations: 301; Topics: Self-Supervised & Representation Learning, Instruction Tuning & SFT, Inference-Time Scaling & Test-Time Compute)
A framework for human evaluation of large language models in healthcare derived from literature review📑: With generative artificial intelligence (GenAI), particularly large language models (LLMs), continuing to make inroads in healthcare, assessing LLMs with human evaluations is essential to assuring ... [May 2024] (Citations: 300; Topics: Evaluation of LLMs & Agents, LLMs for Healthcare & Science, Federated & Personalized AI)
Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models📑: Humans draw to facilitate reasoning: we draw auxiliary lines when solving geometry problems; we mark and circle when reasoning on maps; we use sketches to amplify our ideas and relieve our ... [Jun 2024] (Citations: 299; Topics: Reasoning in LLMs, Multimodal LLMs, Inference-Time Scaling & Test-Time Compute)
ChatGPT for shaping the future of dentistry: the potential of multi-modal large language model📑: The ChatGPT, a lite and conversational variant of Generative Pretrained Transformer 4 (GPT-4) developed by OpenAI, is one of the milestone Large Language Models (LLMs) with billions of parameters. [Apr 2023] (Citations: 298; Topics: LLM Overview & History, Continual Learning & Model Merging)
PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models📑: To parameter-efficiently fine-tune (PEFT) large language models (LLMs), the low-rank adaptation (LoRA) method approximates the model changes $\Delta W \in \mathbb{R}^{m \times n}$ through the product ... [Apr 2024] (Citations: 298; Topics: PEFT & LoRA, Embeddings & Vector Search, Efficient LLMs: Training & Inference)
Continual Learning of Large Language Models: A Comprehensive Survey📑: The challenge of effectively and efficiently adapting statically pre-trained Large Language Models (LLMs) to ever-evolving data distributions remains predominant. [Apr 2024] (Citations: 297; Topics: Continual Learning & Model Merging, Efficient LLMs: Training & Inference, Data for LLMs)
Hybrid Transformers for Music Source Separation📑: A natural question arising in Music Source Separation (MSS) is whether long range contextual information is useful, or whether local acoustic features are sufficient. [Nov 2022] (Citations: 295; Topics: Context Engineering, LLM Architecture Innovations)
Large language models (LLMs): survey, technical frameworks, and future challenges📑: Artificial intelligence (AI) has significantly impacted various fields. (Citations: 295; Topics: LLM Overview & History, Federated & Personalized AI)
A Survey on Vision-Language-Action Models for Embodied AI📑: Embodied AI is widely recognized as a cornerstone of artificial general intelligence (AGI) because it involves controlling embodied agents to perform tasks in the physical world. [May 2024] (Citations: 294; Topics: LLM for Robotics & Embodied AI, LLM Agents, Multimodal LLMs)
Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models📑: We introduce new jailbreak attacks on vision language models (VLMs), which use aligned LLMs and are resilient to text-only jailbreak attacks. [Jul 2023] (Citations: 294; Topics: Trustworthy & Secure LLMs, Multimodal LLMs)
MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries📑: Retrieval-augmented generation (RAG) augments large language models (LLM) by retrieving relevant knowledge, showing promising potential in mitigating LLM hallucinations and enhancing response ... [Jan 2024] (Citations: 293; Topics: Retrieval-Augmented Generation (RAG), Hallucination in LLMs, Evaluation of LLMs & Agents)
Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons📑: We provide a theoretical framework for Reinforcement Learning with Human Feedback (RLHF). [Jan 2023] (Citations: 293; Topics: Alignment & RLHF, RLVR & Process Reward Models, RLAIF & Constitutional AI)
Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts📑: Deep learning for time series forecasting has seen significant advancements over the past decades. [Sep 2024] (Citations: 293; Topics: Mixture of Experts, LLM Overview & History, Multimodal LLMs)
Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study📑: Reinforcement Learning from Human Feedback (RLHF) is currently the most widely used method to align large language models (LLMs) with human preferences. [Apr 2024] (Citations: 292; Topics: Alignment & RLHF, RLAIF & Constitutional AI, RLVR & Process Reward Models)
Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity📑: This survey addresses the crucial issue of factuality in Large Language Models (LLMs). [Oct 2023] (Citations: 291; Topics: Hallucination in LLMs, LLM Overview & History, Embeddings & Vector Search)
Evaluating Large Language Models in Class-Level Code Generation📑: Recently, many large language models (LLMs) have been proposed, showing advanced proficiency in code generation. (Citations: 291; Topics: LLMs for Code)
Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration📑: Human intelligence thrives on cognitive synergy, where collaboration among different minds yield superior outcomes compared to isolated individuals. [Jul 2023] (Citations: 290; Topics: LLM Agents, Continual Learning & Model Merging, Instruction Tuning & SFT)
A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily📑: Large Language Models (LLMs), such as ChatGPT and GPT-4, are designed to provide useful and safe responses. [Nov 2023] (Citations: 290; Topics: LLM Overview & History, Prompt Engineering & In-Context Learning, Trustworthy & Secure LLMs)
From Sparse to Soft Mixtures of Experts📑: Sparse mixture of expert architectures (MoEs) scale model capacity without significant increases in training or inference costs. [Aug 2023] (Citations: 289; Topics: Mixture of Experts, Efficient LLMs: Training & Inference, LLM Architecture Innovations)
Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities📑: Large language models (LLMs) have received considerable attention recently due to their outstanding comprehension and reasoning capabilities, leading to great progress in many fields. [May 2024] (Citations: 288; Topics: LLM Architecture Innovations, Reasoning in LLMs, LLM Overview & History)
Small Language Models are the Future of Agentic AI📑: Large language models (LLMs) are often praised for exhibiting near-human performance on a wide range of tasks and valued for their ability to hold a general conversation. [Jun 2025] (Citations: 288; Topics: LLM Agents, Small Language Models)
Tool learning with large language models: a survey📑: Recently, tool learning with large language models (LLMs) has emerged as a promising paradigm for augmenting the capabilities of LLMs to tackle highly complex problems. [May 2024] (Citations: 287; Topics: Function Calling & Tool Use, LLM Overview & History, RLVR & Process Reward Models)
A Survey on Video Diffusion Models📑: The recent wave of AI-generated content (AIGC) has witnessed substantial success in computer vision, with the diffusion model playing a crucial role in this achievement. [Oct 2023] (Citations: 285; Topics: LLM Overview & History, Multimodal LLMs)
Jailbreak Attacks and Defenses Against Large Language Models: A Survey📑: Large Language Models (LLMs) have performed exceptionally in various text-generative tasks, including question answering, translation, code completion, etc. [Jul 2024] (Citations: 283; Topics: Trustworthy & Secure LLMs, LLMs for Code, LLM Overview & History)
RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs📑: Large language models (LLMs) typically utilize the top-k contexts from a retriever in retrieval-augmented generation (RAG). [Jul 2024] (Citations: 282; Topics: Retrieval-Augmented Generation (RAG), Context Engineering, GraphRAG & Knowledge Graphs)
PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance📑: Although large language models (LLMs) has shown great performance on natural language processing (NLP) in the financial domain, there are no publicly available financial tailtored LLMs, instruction ... [Jun 2023] (Citations: 282; Topics: Evaluation of LLMs & Agents, Instruction Tuning & SFT, Data for LLMs)
Layer by Layer: Uncovering Hidden Representations in Language Models📑: From extracting features to generating text, the outputs of large language models (LLMs) typically rely on the final layers, following the conventional wisdom that earlier layers capture only ... [Feb 2025] (Citations: 279; Topics: LLM Overview & History)
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding📑: We present LayerSkip, an end-to-end solution to speed-up inference of large language models (LLMs). [Apr 2024] (Citations: 279; Topics: Efficient LLMs: Training & Inference, Instruction Tuning & SFT, Inference-Time Scaling & Test-Time Compute)
LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models📑: Large language models (LLMs) have been applied in various applications due to their astonishing capabilities. [Oct 2023] (Citations: 279; Topics: Prompt Engineering & In-Context Learning, Efficient LLMs: Training & Inference)
Reinforcement Learning for Reasoning in Large Language Models with One Training Example📑: We show that reinforcement learning with verifiable reward using one training example (1-shot RLVR) is effective in incentivizing the math reasoning capabilities of large language models (LLMs). [Apr 2025] (Citations: 278; Topics: Reasoning in LLMs, RLVR & Process Reward Models, RLAIF & Constitutional AI)
SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models📑: In this work, we introduce SMART-LLM, an innovative framework designed for embodied multi-robot task planning. [Sep 2023] (Citations: 277; Topics: LLM Agents, LLM for Robotics & Embodied AI, Continual Learning & Model Merging)
Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning📑: This paper presents a systematic overview of parameter-efficient fine-tuning methods, covering over 50 papers published between early 2019 and mid-2024. [Mar 2023] (Citations: 277; Topics: PEFT & LoRA, Efficient LLMs: Training & Inference, LLM Overview & History)
Secrets of RLHF in Large Language Models Part I: PPO📑: Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. [Jul 2023] (Citations: 277; Topics: Alignment & RLHF, Federated & Personalized AI)
DriveMLM: aligning multi-modal large language models with behavioral planning states for autonomous driving📑: Large language models (LLMs) have opened up new possibilities for intelligent agents, endowing them with human-like thinking and cognitive abilities. [Dec 2023] (Citations: 277; Topics: LLM Agents, Inference-Time Scaling & Test-Time Compute)
SEED-Bench: Benchmarking Multimodal Large Language Models📑 (Citations: 277; Topics: Evaluation of LLMs & Agents, Multimodal LLMs)
Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions📑: We study joint video and language (VL) pretraining to enable cross-modality learning and benefit plentiful downstream VL tasks. [Nov 2021] (Citations: 276; Topics: Multimodal LLMs, Self-Supervised & Representation Learning)
An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models📑 (Citations: 276; Topics: Scaling Laws, Inference-Time Scaling & Test-Time Compute, Efficient LLMs: Training & Inference)
Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph📑: Although large language models (LLMs) have achieved significant success in various tasks, they often struggle with hallucination problems, especially in scenarios requiring deep and responsible ... [Jul 2023] (Citations: 275; Topics: GraphRAG & Knowledge Graphs, Reasoning in LLMs, Hallucination in LLMs)
Chain-of-Thought Reasoning Without Prompting📑: In enhancing the reasoning capabilities of large language models (LLMs), prior research primarily focuses on specific prompting techniques such as few-shot or zero-shot chain-of-thought (CoT) ... [Feb 2024] (Citations: 275; Topics: Prompt Engineering & In-Context Learning, Reasoning in LLMs, Inference-Time Scaling & Test-Time Compute)
Large Language Models for Code: Security Hardening and Adversarial Testing📑: Large language models (large LMs) are increasingly trained on massive codebases and used to generate code. [Feb 2023] (Citations: 275; Topics: Trustworthy & Secure LLMs, LLMs for Code)
JudgeBench: A Benchmark for Evaluating LLM-based Judges📑: LLM-based judges have emerged as a scalable alternative to human evaluation and are increasingly used to assess, compare, and improve models. [Oct 2024] (Citations: 275; Topics: Evaluation of LLMs & Agents, LLM Agents, Instruction Tuning & SFT)
A Survey on ChatGPT: AI–Generated Contents, Challenges, and Solutions📑: With the widespread use of large artificial intelligence (AI) models such as ChatGPT, AI-generated content (AIGC) has garnered increasing attention and is leading a paradigm shift in content creation ... [May 2023] (Citations: 273; Topics: LLM Overview & History, LLM Architecture Innovations, Federated & Personalized AI)
From System 1 to System 2: A Survey of Reasoning Large Language Models📑: Achieving human-level intelligence requires refining the transition from the fast, intuitive System 1 to the slower, more deliberate System 2 reasoning. [Feb 2025] (Citations: 273; Topics: Reasoning in LLMs, LLM Overview & History, RLVR & Process Reward Models)
LVLM-EHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models📑: Large Vision-Language Models (LVLMs) have recently played a dominant role in multimodal vision-language learning. [Jun 2023] (Citations: 273; Topics: Evaluation of LLMs & Agents, Multimodal LLMs, LLM Agents)
Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging📑: While Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with general, aggregate human preferences, it is suboptimal for learning diverse, individual perspectives. [Oct 2023] (Citations: 273; Topics: Alignment & RLHF, RLAIF & Constitutional AI, Federated & Personalized AI)
MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models📑: The security concerns surrounding Large Language Models (LLMs) have been extensively explored, yet the safety of Multimodal Large Language Models (MLLMs) remains understudied. [Nov 2023] (Citations: 272; Topics: Evaluation of LLMs & Agents, Trustworthy & Secure LLMs, Multimodal LLMs)
Continual Lifelong Learning in Natural Language Processing: A Survey📑: Continual learning (CL) aims to enable information systems to learn from a continuous data stream across time. [Dec 2020] (Citations: 271; Topics: Continual Learning & Model Merging, Data for LLMs, LLM Overview & History)
LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models📑: We present LongLoRA, an efficient fine-tuning approach that extends the context sizes of pre-trained large language models (LLMs), with limited computation cost. [Sep 2023] (Citations: 271; Topics: PEFT & LoRA, Efficient LLMs: Training & Inference, Context Engineering)
Self-Supervised Learning for Multimedia Recommendation📑: Learning representations for multimedia content is critical for multimedia recommendation. (Citations: 271; Topics: Self-Supervised & Representation Learning, Instruction Tuning & SFT)
Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks📑: Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. [Oct 2023] (Citations: 270; Topics: Trustworthy & Secure LLMs, LLM Overview & History, LLM Architecture Innovations)
What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks📑: Large Language Models (LLMs) with strong abilities in natural language processing tasks have emerged and have been applied in various kinds of areas such as science, finance and software engineering. [May 2023] (Citations: 270; Topics: LLMs for Healthcare & Science, Evaluation of LLMs & Agents, LLMs for Code)
Query Rewriting for Retrieval-Augmented Large Language Models📑: Large Language Models (LLMs) play powerful, black-box readers in the retrieve-then-read pipeline, making remarkable progress in knowledge-intensive tasks. [May 2023] (Citations: 268; Topics: Retrieval-Augmented Generation (RAG), GraphRAG & Knowledge Graphs, Context Engineering)
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach📑: We study a novel language model architecture that is capable of scaling test-time computation by implicitly reasoning in latent space. [Feb 2025] (Citations: 267; Topics: Inference-Time Scaling & Test-Time Compute, Reasoning in LLMs, LLM Architecture Innovations)
Large Language Models Meet NL2Code: A Survey📑: The task of generating code from a natural language description, or NL2Code, is considered a pressing and significant challenge in code intelligence. [Dec 2022] (Citations: 266; Topics: LLMs for Code, LLM Overview & History)
Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment📑: Larger language models (LLMs) have taken the world by storm with their massive multi-tasking capabilities simply by optimizing over a next-word prediction objective. [Aug 2023] (Citations: 266; Topics: Trustworthy & Secure LLMs, Alignment & RLHF)
RoCo: Dialectic Multi-Robot Collaboration with Large Language Models📑: We propose a novel approach to multi-robot collaboration that harnesses the power of pre-trained large language models (LLMs) for both high-level communication and low-level path planning. [Jul 2023] (Citations: 266; Topics: LLM for Robotics & Embodied AI, LLM Agents)
Factuality challenges in the era of large language models and opportunities for fact-checking📑: The emergence of tools based on large language models (LLMs), such as OpenAI’s ChatGPT and Google’s Gemini, has garnered immense public attention owing to their advanced natural language generation ... [Oct 2023] (Citations: 266; Topics: Hallucination in LLMs)
Knowledge Editing for Large Language Models: A Survey📑: Large Language Models (LLMs) have recently transformed both the academic and industrial landscapes due to their remarkable capacity to understand, analyze, and generate texts based on their vast ... [Oct 2023] (Citations: 265; Topics: Continual Learning & Model Merging, LLM Overview & History)
Learning Video Representations from Large Language Models📑: We introduce LAVILA, a new approach to learning video-language representations by leveraging Large Language Models (LLMs). [Dec 2022] (Citations: 265; Topics: Multimodal LLMs, Self-Supervised & Representation Learning)
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases📑: This paper addresses the growing need for efficient large language models (LLMs) on mobile devices, driven by increasing cloud costs and latency concerns. [Feb 2024] (Citations: 265; Topics: Small Language Models, Efficient LLMs: Training & Inference, PEFT & LoRA)
A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation📑: Recently developed large language models have achieved remarkable success in generating fluent and coherent text. [Jul 2023] (Citations: 264; Topics: Hallucination in LLMs, Retrieval-Augmented Generation (RAG), Inference-Time Scaling & Test-Time Compute)
Deliberative Alignment: Reasoning Enables Safer Language Models📑: As large-scale language models increasingly impact safety-critical domains, ensuring their reliable adherence to well-defined principles remains a fundamental challenge. [Dec 2024] (Citations: 264; Topics: Alignment & RLHF, Reasoning in LLMs, Trustworthy & Secure LLMs)
Scalable watermarking for identifying large language model outputs📑: Large language models (LLMs) have enabled the generation of high-quality synthetic text, often indistinguishable from human-written content, at a scale that can markedly affect the nature of the ... (Citations: 264; Topics: Retrieval-Augmented Generation (RAG))
Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters📑: Continual learning can empower vision-language models to continuously acquire new knowledge, without the need for access to the entire historical dataset. [Mar 2024] (Citations: 264; Topics: Mixture of Experts, Multimodal LLMs, Continual Learning & Model Merging)
Mobile Edge Intelligence for Large Language Models: A Contemporary Survey📑: On-device large language models (LLMs), referring to running LLMs on edge devices, have raised considerable interest since they are more cost-effective, latency-efficient, and privacy-preserving ... [Jul 2024] (Citations: 264; Topics: Efficient LLMs: Training & Inference, Small Language Models, LLMOps & Model Serving)
Self-supervised learning methods and applications in medical imaging analysis: a survey📑: The scarcity of high-quality annotated medical imaging datasets is a major problem that collides with machine learning applications in the field of medical imaging analysis and impedes its ... [Sep 2021] (Citations: 263; Topics: Self-Supervised & Representation Learning, LLMs for Healthcare & Science, Data for LLMs)
L-Eval: Instituting Standardized Evaluation for Long Context Language Models📑: Recently, there has been growing interest in extending the context length of large language models (LLMs), aiming to effectively process long inputs of one turn or conversations with more extensive ... [Jul 2023] (Citations: 263; Topics: Context Engineering, Evaluation of LLMs & Agents)
From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function📑: Reinforcement Learning From Human Feedback (RLHF) has been critical to the success of the latest generation of generative AI models. [Apr 2024] (Citations: 263; Topics: Alignment & RLHF, RLVR & Process Reward Models, RLAIF & Constitutional AI)
Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding📑: Table-based reasoning with large language models (LLMs) is a promising direction to tackle many table understanding tasks, such as table-based question answering and fact verification. [Jan 2024] (Citations: 263; Topics: Tabular Data & NL2SQL, Reasoning in LLMs, Inference-Time Scaling & Test-Time Compute)
Self-Play Preference Optimization for Language Model Alignment📑: Standard reinforcement learning from human feedback (RLHF) approaches relying on parametric models like the Bradley-Terry model fall short in capturing the intransitivity and irrationality in human ... [May 2024] (Citations: 262; Topics: Alignment & RLHF, RLAIF & Constitutional AI, RLVR & Process Reward Models)
Physically Grounded Vision-Language Models for Robotic Manipulation📑: Recent advances in vision-language models (VLMs) have led to improved performance on tasks such as visual question answering and image captioning. [Sep 2023] (Citations: 261; Topics: Multimodal LLMs, LLM for Robotics & Embodied AI, Tabular Data & NL2SQL)
On Hallucination and Predictive Uncertainty in Conditional Language Generation📑: Despite improvements in performances on different natural language generation tasks, deep neural models are prone to hallucinating facts that are incorrect or nonexistent. [Mar 2021] (Citations: 260; Topics: Hallucination in LLMs)
Impact of word embedding models on text analytics in deep learning environment: a review📑: The selection of word embedding and deep learning models for better outcomes is vital. (Citations: 260; Topics: Embeddings & Vector Search, Multimodal LLMs)
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads📑: Deploying long-context large language models (LLMs) is essential but poses significant computational and memory challenges. [Oct 2024] (Citations: 259; Topics: Efficient LLMs: Training & Inference, LLM Architecture Innovations, LLM Memory & Personalization)
Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future📑: Reasoning, a fundamental cognitive process integral to human intelligence, has garnered substantial interest within artificial intelligence. [Sep 2023] (Citations: 258; Topics: Reasoning in LLMs, LLM Overview & History, Inference-Time Scaling & Test-Time Compute)
Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback📑: We study whether multiple large language models (LLMs) can autonomously improve each other in a negotiation game by playing, reflecting, and criticizing. [May 2023] (Citations: 257; Topics: RLAIF & Constitutional AI, Prompt Engineering & In-Context Learning, LLM Agents)
Direct Language Model Alignment from Online AI Feedback📑: Direct alignment from preferences (DAP) methods, such as DPO, have recently emerged as efficient alternatives to reinforcement learning from human feedback (RLHF), that do not require a separate ... [Feb 2024] (Citations: 257; Topics: Alignment & RLHF, RLAIF & Constitutional AI, RLVR & Process Reward Models)
Vision-language models for medical report generation and visual question answering: a review📑: Medical vision-language models (VLMs) combine computer vision (CV) and natural language processing (NLP) to analyze visual and textual medical data. [Mar 2024] (Citations: 257; Topics: Multimodal LLMs, LLMs for Healthcare & Science, Data for LLMs)
The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning📑: Does prompting a large language model (LLM) like GPT-3 with explanations improve in-context learning? [May 2022] (Citations: 256; Topics: Prompt Engineering & In-Context Learning, Reasoning in LLMs, RLVR & Process Reward Models)
Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards📑: Foundation models are first pre-trained on vast unsupervised datasets and then fine-tuned on labeled data. [Jun 2023] (Citations: 255; Topics: Data for LLMs, LLM Overview & History, Alignment & RLHF)
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models📑: Recurrent neural networks (RNNs) have fast inference and scale efficiently on long sequences, but they are difficult to train and hard to scale. [Feb 2024] (Citations: 255; Topics: Efficient LLMs: Training & Inference, LLM Architecture Innovations, GraphRAG & Knowledge Graphs)
Open-vocabulary Queryable Scene Representations for Real World Planning📑: Large language models (LLMs) have unlocked new capabilities of task planning from human instructions. [Sep 2022] (Citations: 254; Topics: LLM Agents, Instruction Tuning & SFT, Alignment & RLHF)
Seven Failure Points When Engineering a Retrieval Augmented Generation System📑: Software engineers are increasingly adding semantic search capabilities to applications using a strategy known as Retrieval Augmented Generation (RAG). [Jan 2024] (Citations: 254; Topics: Retrieval-Augmented Generation (RAG), Context Engineering, GraphRAG & Knowledge Graphs)
Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects📑: Self-supervised learning (SSL) has recently achieved impressive performance on various time series tasks. [Jun 2023] (Citations: 254; Topics: Self-Supervised & Representation Learning, Instruction Tuning & SFT, Inference-Time Scaling & Test-Time Compute)
Woodpecker: hallucination correction for multimodal large language models📑: Hallucinations is a big shadow hanging over the rapidly evolving multimodal large language models (MLLMs), referring to that the generated text is inconsistent with the image content. [Oct 2023] (Citations: 254; Topics: Multimodal LLMs, Hallucination in LLMs, LLM Overview & History)
Jigsaw: Large Language Models meet Program Synthesis📑: Large pre-trained language models such as GPT-3 [10], Codex [11], and Coogle's language model [7] are now capable of generating code from natural language specifications of programmer intent. [Dec 2021] (Citations: 252; Topics: LLMs for Code)
Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization📑: Existing open-source multimodal large language models (MLLMs) generally follow a training process involving pre-training and supervised fine-tuning. [Nov 2024] (Citations: 252; Topics: Multimodal LLMs, Alignment & RLHF, Reasoning in LLMs)
LooGLE: Can Long-Context Language Models Understand Long Contexts?📑: Large language models (LLMs), despite their impressive performance in various language tasks, are typically limited to processing texts within context-window size. [Nov 2023] (Citations: 251; Topics: Context Engineering, Scaling Laws)
Chain of Agents: Large Language Models Collaborating on Long-Context Tasks📑: Addressing the challenge of effectively processing long contexts has become a critical issue for Large Language Models (LLMs). [Jun 2024] (Citations: 251; Topics: LLM Agents, Context Engineering, LLM Memory & Personalization)
Planning with Large Language Models for Code Generation📑: Existing large language model-based code generation pipelines typically use beam search or sampling algorithms during the decoding process. [Mar 2023] (Citations: 250; Topics: LLMs for Code, LLM Agents)
R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning📑: Existing Large Reasoning Models (LRMs) have shown the potential of reinforcement learning (RL) to enhance the complex reasoning capabilities of Large Language Models~(LLMs). [Mar 2025] (Citations: 250; Topics: Reasoning in LLMs, RLVR & Process Reward Models, RLAIF & Constitutional AI)
Knowledge-enhanced visual-language pre-training on chest radiology images📑: While multi-modal foundation models pre-trained on large-scale data have been successful in natural language understanding and vision recognition, their use in medical domains is still limited due to ... [Feb 2023] (Citations: 249; Topics: Multimodal LLMs, LLM Overview & History, LLMs for Healthcare & Science)
GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information📑: While large language models (LLMs) have been successfully applied to various tasks, they still face challenges with hallucinations. [Apr 2023] (Citations: 248; Topics: Hallucination in LLMs, LLMs for Healthcare & Science, Function Calling & Tool Use)
ProcessBench: Identifying Process Errors in Mathematical Reasoning📑: As language models regularly make mistakes when solving math problems, automated identification of errors in the reasoning process becomes increasingly significant for their scalable oversight. [Dec 2024] (Citations: 248; Topics: Reasoning in LLMs, Evaluation of LLMs & Agents, RLVR & Process Reward Models)
DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning📑: Large Vision-Language Models excel at multimodal understanding but struggle to deeply integrate visual information into their predominantly text-based reasoning processes, a key challenge in ... [May 2025] (Citations: 248; Topics: Multimodal LLMs, Reasoning in LLMs, Inference-Time Scaling & Test-Time Compute)
SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression📑: The advancements in Large Language Models (LLMs) have been hindered by their substantial sizes, which necessitates LLM compression methods for practical deployment. [Mar 2024] (Citations: 247; Topics: Efficient LLMs: Training & Inference, LLMOps & Model Serving)
RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics📑: From rearranging objects on a table to putting groceries into shelves, robots must plan precise action points to perform tasks accurately and reliably. [Jun 2024] (Citations: 247; Topics: LLM for Robotics & Embodied AI, Multimodal LLMs, Tabular Data & NL2SQL)
Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback📑: A key technology for the development of large language models (LLMs) involves instruction tuning that helps align the models' responses with human expectations to realize impressive learning ... [Jul 2023] (Citations: 246; Topics: Instruction Tuning & SFT, Alignment & RLHF, RLVR & Process Reward Models)
SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models📑: In the rapidly evolving landscape of Large Language Models (LLMs), ensuring robust safety measures is paramount. [Feb 2024] (Citations: 246; Topics: Evaluation of LLMs & Agents, Trustworthy & Secure LLMs)
CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving📑: As large language models (LLMs) take on complex tasks, their inputs are supplemented with longer contexts that incorporate domain knowledge. [Oct 2023] (Citations: 246; Topics: Efficient LLMs: Training & Inference, LLM Architecture Innovations, LLMOps & Model Serving)
Foundation Models for Decision Making: Problems, Methods, and Opportunities📑: Foundation models pretrained on diverse data at scale have demonstrated extraordinary capabilities in a wide range of vision and language tasks. [Mar 2023] (Citations: 245; Topics: LLM Overview & History, Data for LLMs, Multimodal LLMs)
SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models📑: Most of the existing Large Language Model (LLM) benchmarks on scientific problem reasoning focus on problems grounded in high-school subjects and are confined to elementary algebraic operations. [Jul 2023] (Citations: 245; Topics: Evaluation of LLMs & Agents, Reasoning in LLMs, RLVR & Process Reward Models)
HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs📑: The breakthrough of OpenAI o1 highlights the potential of enhancing reasoning to improve LLM. [Dec 2024] (Citations: 245; Topics: LLMs for Healthcare & Science, Reasoning in LLMs, Inference-Time Scaling & Test-Time Compute)
RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning📑: Training large language models (LLMs) as interactive agents presents unique challenges including long-horizon decision making and interacting with stochastic environment feedback. [Apr 2025] (Citations: 245; Topics: LLM Agents, RLAIF & Constitutional AI, RLVR & Process Reward Models)
Query2doc: Query Expansion with Large Language Models📑: This paper introduces a simple yet effective query expansion approach, denoted as query2doc, to improve both sparse and dense retrieval systems. [Mar 2023] (Citations: 244; Topics: Embeddings & Vector Search, Retrieval-Augmented Generation (RAG), LLM Architecture Innovations)
Revisiting Relation Extraction in the era of Large Language Models📑: Relation extraction (RE) is the core NLP task of inferring semantic relationships between entities from text. [May 2023] (Citations: 243; Topics: LLM Overview & History)
Evolutionary optimization of model merging recipes📑: Large language models (LLMs) have become increasingly capable, but their development often requires substantial computational resources. [Mar 2024] (Citations: 241; Topics: Continual Learning & Model Merging)
Rotary Position Embedding for Vision Transformer📑: Rotary Position Embedding (RoPE) performs remarkably on language models, especially for length extrapolation of Transformers. [Mar 2024] (Citations: 241; Topics: LLM Architecture Innovations, Embeddings & Vector Search)
JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks📑: With the rapid advancements in Multimodal Large Language Models (MLLMs), securing these models against malicious inputs while aligning them with human values has emerged as a critical challenge. [Apr 2024] (Citations: 240; Topics: Evaluation of LLMs & Agents, Multimodal LLMs, Trustworthy & Secure LLMs)
CodeGen2: Lessons for Training LLMs on Programming and Natural Languages📑: Large language models (LLMs) have demonstrated remarkable abilities in representation learning for program synthesis and understanding tasks. [May 2023] (Citations: 239; Topics: LLMs for Code, Self-Supervised & Representation Learning)
FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving📑: Transformers, driven by attention mechanisms, form the foundation of large language models (LLMs). [Jan 2025] (Citations: 239; Topics: Efficient LLMs: Training & Inference, LLMOps & Model Serving, LLM Architecture Innovations)
ChatEDA: A Large Language Model Powered Autonomous Agent for EDA📑: The integration of a complex set of electronic design automation (EDA) tools to enhance interoperability is a critical concern for circuit designers. [Aug 2023] (Citations: 238; Topics: LLM Agents, Function Calling & Tool Use, GUI Agents)
Training Language Models to Reason Efficiently📑: Scaling model size and training data has led to great advances in the performance of Large Language Models (LLMs). [Feb 2025] (Citations: 238; Topics: Efficient LLMs: Training & Inference, Data for LLMs, Scaling Laws)
Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization📑: Multimodal large language models have made significant advancements in recent years, yet they still suffer from a common issue known as the"hallucination problem", in which the models generate ... [Nov 2023] (Citations: 237; Topics: Hallucination in LLMs, Alignment & RLHF, Multimodal LLMs)
Nash Learning from Human Feedback📑: Reinforcement learning from human feedback (RLHF) has emerged as the main paradigm for aligning large language models (LLMs) with human preferences. [Dec 2023] (Citations: 237; Topics: Alignment & RLHF, RLAIF & Constitutional AI, RLVR & Process Reward Models)
DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models📑: A long-standing goal of AI systems is to perform complex multimodal reasoning like humans. [Oct 2023] (Citations: 237; Topics: Reasoning in LLMs, Prompt Engineering & In-Context Learning, Multimodal LLMs)
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models📑: Language has long been conceived as an essential tool for human reasoning. [Jan 2025] (Citations: 236; Topics: Reasoning in LLMs, LLM Overview & History, Function Calling & Tool Use)
Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning📑: A promising approach for improving reasoning in large language models is to use process reward models (PRMs). [Oct 2024] (Citations: 236; Topics: Reasoning in LLMs, RLVR & Process Reward Models, Alignment & RLHF)
A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models📑 (Citations: 235; Topics: Prompt Engineering & In-Context Learning, LLM Overview & History, Multimodal LLMs)
Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding - A Survey📑: Recent breakthroughs in large language modeling have facilitated rigorous exploration of their application in diverse tasks related to tabular data modeling, such as prediction, tabular data ... [Feb 2024] (Citations: 235; Topics: Tabular Data & NL2SQL, Data for LLMs, LLM Overview & History)
DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition📑: We introduce DeepSeek-Prover-V2, an open-source large language model designed for formal theorem proving in Lean 4, with initialization data collected through a recursive theorem proving pipeline ... [Apr 2025] (Citations: 235; Topics: Reasoning in LLMs, RLVR & Process Reward Models, Data for LLMs)
Self-Planning Code Generation with Large Language Models📑: Although large language models (LLMs) have demonstrated impressive ability in code generation, they are still struggling to address the complicated intent provided by humans. [Mar 2023] (Citations: 234; Topics: LLMs for Code, LLM Agents, Instruction Tuning & SFT)
Next-Generation Database Interfaces: A Survey of LLM-Based Text-to-SQL📑: Generating accurate SQL from users’ natural language questions (text-to-SQL) remains a long-standing challenge due to the complexities involved in user question understanding, database schema ... [Jun 2024] (Citations: 234; Topics: Tabular Data & NL2SQL, LLM Overview & History, Hallucination in LLMs)
Reward Model Ensembles Help Mitigate Overoptimization📑: Reinforcement learning from human feedback (RLHF) is a standard approach for fine-tuning large language models to follow instructions. [Oct 2023] (Citations: 233; Topics: Alignment & RLHF, Instruction Tuning & SFT, RLVR & Process Reward Models)
Benchmarking Large Language Models for Automated Verilog RTL Code Generation📑: Automating hardware design could obviate a signif-icant amount of human error from the engineering process and lead to fewer errors. [Dec 2022] (Citations: 233; Topics: LLMs for Code, Evaluation of LLMs & Agents)
Progressive Prompts: Continual Learning for Language Models📑: We introduce Progressive Prompts - a simple and efficient approach for continual learning in language models. [Jan 2023] (Citations: 232; Topics: Continual Learning & Model Merging, Prompt Engineering & In-Context Learning, Efficient LLMs: Training & Inference)
Benchmarking Self-Supervised Learning on Diverse Pathology Datasets📑: Computational pathology can lead to saving human lives, but models are annotation hungry and pathology images are notoriously expensive to annotate. [Dec 2022] (Citations: 232; Topics: Self-Supervised & Representation Learning, Evaluation of LLMs & Agents, Multimodal LLMs)
LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models📑: Quantization is an indispensable technique for serving Large Language Models (LLMs) and has recently found its way into LoRA fine-tuning. [Oct 2023] (Citations: 232; Topics: Efficient LLMs: Training & Inference, PEFT & LoRA, LLMOps & Model Serving)
Active Prompting with Chain-of-Thought for Large Language Models📑: The increasing scale of large language models (LLMs) brings emergent abilities to various complex tasks requiring reasoning, such as arithmetic and commonsense reasoning. [Feb 2023] (Citations: 232; Topics: Reasoning in LLMs, Prompt Engineering & In-Context Learning, Scaling Laws)
Generative AI Agents With Large Language Model for Satellite Networks via a Mixture of Experts Transmission📑: In response to the needs of 6G global communications, satellite communication networks have emerged as a key solution. [Apr 2024] (Citations: 232; Topics: LLM Agents, Mixture of Experts)
Personality Traits in Large Language Models📑: The advent of large language models (LLMs) has revolutionized natural language processing, enabling the generation of coherent and contextually relevant human-like text. [Jul 2023] (Citations: 231; Topics: Hallucination in LLMs, Retrieval-Augmented Generation (RAG), Context Engineering)
Efficient Self-supervised Vision Transformers for Representation Learning📑: This paper investigates two techniques for developing efficient self-supervised vision transformers (EsViT) for visual representation learning. [Jun 2021] (Citations: 230; Topics: Self-Supervised & Representation Learning, Efficient LLMs: Training & Inference, Multimodal LLMs)
Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations📑: Recommender models capture ever-changing user preferences by training with in-domain user behavior data. [Aug 2023] (Citations: 230; Topics: LLM Memory & Personalization, LLM Agents, Alignment & RLHF)
Large Language Models are few(1)-shot Table Reasoners📑: Recent literature has shown that large language models (LLMs) are generally excellent few-shot reasoners to solve text reasoning tasks. [Oct 2022] (Citations: 229; Topics: Prompt Engineering & In-Context Learning, Reasoning in LLMs, Tabular Data & NL2SQL)
The benefits, risks and bounds of personalizing the alignment of large language models to individuals📑 (Citations: 229; Topics: Alignment & RLHF)
COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining📑: We present a self-supervised learning framework, COCO-LM, that pretrains Language Models by COrrecting and COntrasting corrupted text sequences. [Feb 2021] (Citations: 227; Topics: Self-Supervised & Representation Learning, Instruction Tuning & SFT)
A Survey of Knowledge Enhanced Pre-Trained Language Models📑: Pre-trained Language Models (PLMs) which are trained on large text corpus via self-supervised learning method, have yielded promising performance on various tasks in Natural Language Processing (NLP). [Nov 2022] (Citations: 227; Topics: Self-Supervised & Representation Learning, LLM Overview & History, GraphRAG & Knowledge Graphs)
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution📑: The recent DeepSeek-R1 release has demonstrated the immense potential of reinforcement learning (RL) in enhancing the general reasoning capabilities of large language models (LLMs). [Feb 2025] (Citations: 227; Topics: Reasoning in LLMs, RLVR & Process Reward Models, RLAIF & Constitutional AI)
Prompting Large Language Models with Speech Recognition Abilities📑: Large language models (LLMs) have proven themselves highly flexible, able to solve a wide range of generative tasks, such as abstractive summarization and open-ended question answering. [Jul 2023] (Citations: 227; Topics: Prompt Engineering & In-Context Learning, Tabular Data & NL2SQL, GraphRAG & Knowledge Graphs)
Scaling Large-Language-Model-based Multi-Agent Collaboration📑: Recent breakthroughs in large language model-driven autonomous agents have revealed that multi-agent collaboration often surpasses each individual through collective reasoning. [Jun 2024] (Citations: 227; Topics: LLM Agents, Reasoning in LLMs, Inference-Time Scaling & Test-Time Compute)
VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks📑: We present VAPO, Value-based Augmented Proximal Policy Optimization framework for reasoning models. [Apr 2025] (Citations: 226; Topics: Reasoning in LLMs, RLVR & Process Reward Models, Efficient LLMs: Training & Inference)
Revolutionizing Cyber Threat Detection With Large Language Models: A Privacy-Preserving BERT-Based Lightweight Model for IoT/IIoT Devices📑: The field of Natural Language Processing (NLP) is currently undergoing a revolutionary transformation driven by the power of pre-trained Large Language Models (LLMs) based on groundbreaking ... [Jun 2023] (Citations: 226; Topics: Efficient LLMs: Training & Inference, Trustworthy & Secure LLMs, LLMOps & Model Serving)
The Unreasonable Ineffectiveness of the Deeper Layers📑: How is knowledge stored in an LLM's weights? [Mar 2024] (Citations: 225; Topics: LLM Overview & History)
Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods📑: With extensive pretrained knowledge and high-level general capabilities, large language models (LLMs) emerge as a promising avenue to augment reinforcement learning (RL) in aspects, such as multitask ... [Apr 2024] (Citations: 225; Topics: RLVR & Process Reward Models, LLM Overview & History, GraphRAG & Knowledge Graphs)
SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks📑: We introduce SwiftSage, a novel agent framework inspired by the dual-process theory of human cognition, designed to excel in action planning for complex interactive reasoning tasks. [May 2023] (Citations: 224; Topics: LLM Agents, Reasoning in LLMs, Inference-Time Scaling & Test-Time Compute)
Compositional Chain-of-Thought Prompting for Large Multimodal Models📑: The combination of strong visual backbones and Large Language Model (LLM) reasoning has led to Large Multimodal Models (LMMs) becoming the current standard for a wide range of vision and language ... [Nov 2023] (Citations: 223; Topics: Reasoning in LLMs, Prompt Engineering & In-Context Learning, Multimodal LLMs)
Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code📑: The rise of Large Language Models (LLMs) has significantly advanced various applications on software engineering tasks, particularly in code generation. [Apr 2024] (Citations: 222; Topics: LLMs for Code, Hallucination in LLMs, Prompt Engineering & In-Context Learning)
QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving📑: Quantization can accelerate large language model (LLM) inference. [May 2024] (Citations: 222; Topics: Efficient LLMs: Training & Inference, LLMOps & Model Serving)
GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents📑: Existing efforts in building Graphical User Interface (GUI) agents largely rely on the training paradigm of supervised fine-tuning on Large Vision-Language Models (LVLMs). [Apr 2025] (Citations: 221; Topics: GUI Agents, LLM Agents, Multimodal LLMs)
ART: Automatic multi-step reasoning and tool-use for large language models📑: Large language models (LLMs) can perform complex reasoning in few- and zero-shot settings by generating intermediate chain of thought (CoT) reasoning steps. [Mar 2023] (Citations: 220; Topics: Reasoning in LLMs, Function Calling & Tool Use, Prompt Engineering & In-Context Learning)
On Decoder-Only Architecture For Speech-to-Text and Large Language Model Integration📑: Large language models (LLMs) have achieved remarkable success in the field of natural language processing, enabling better human-computer interaction using natural language. [Jul 2023] (Citations: 220; Topics: LLM Architecture Innovations)
Self-Guided Contrastive Learning for BERT Sentence Representations📑: Although BERT and its variants have reshaped the NLP landscape, it still remains unclear how best to derive sentence embeddings from such pre-trained Transformers. [Jun 2021] (Citations: 218; Topics: Embeddings & Vector Search, Self-Supervised & Representation Learning, RLVR & Process Reward Models)
Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learning📑: Code comment generation aims at generating natural language descriptions for a code snippet to facilitate developers' program comprehension activities. [Apr 2023] (Citations: 217; Topics: Prompt Engineering & In-Context Learning, LLMs for Code, Hallucination in LLMs)
RedPajama: an Open Dataset for Training Large Language Models📑: Large language models are increasingly becoming a cornerstone technology in artificial intelligence, the sciences, and society as a whole, yet the optimal strategies for dataset composition and ... [Nov 2024] (Citations: 217; Topics: LLMs for Healthcare & Science, Data for LLMs, Federated & Personalized AI)
OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning📑: Trained on massive publicly available data, large language models (LLMs) have demonstrated tremendous success across various fields. [Feb 2024] (Citations: 217; Topics: Federated & Personalized AI, Data for LLMs)
Extreme Compression of Large Language Models via Additive Quantization📑: The emergence of accurate open large language models (LLMs) has led to a race towards performant quantization techniques which can enable their execution on end-user devices. [Jan 2024] (Citations: 217; Topics: Efficient LLMs: Training & Inference)
A review of large language models and autonomous agents in chemistry📑: Large language models (LLMs) have emerged as powerful tools in chemistry, significantly impacting molecule design, property prediction, and synthesis optimization. [Jul 2024] (Citations: 216; Topics: LLM Agents, Function Calling & Tool Use, LLMs for Healthcare & Science)
The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)📑: Retrieval-augmented generation (RAG) is a powerful technique to facilitate language model with proprietary and private data, where data privacy is a pivotal concern. [Feb 2024] (Citations: 216; Topics: Retrieval-Augmented Generation (RAG), Federated & Personalized AI, Data for LLMs)
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors📑: Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. [Jun 2024] (Citations: 216; Topics: Evaluation of LLMs & Agents, Trustworthy & Secure LLMs, LLMOps & Model Serving)
Applying Large Language Models and Chain-of-Thought for Automatic Scoring📑: This study investigates the application of large language models (LLMs), specifically GPT-3. [Dec 2023] (Citations: 216; Topics: Reasoning in LLMs, Inference-Time Scaling & Test-Time Compute, Prompt Engineering & In-Context Learning)
Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework📑: As large language models (LLMs) have become the norm in NLP, demonstrating good performance in generation and reasoning tasks, one of its most fatal disadvantages is the lack of factual correctness. [May 2023] (Citations: 215; Topics: Reasoning in LLMs, GraphRAG & Knowledge Graphs, Prompt Engineering & In-Context Learning)
Measuring Progress on Scalable Oversight for Large Language Models📑: Developing safe and useful general-purpose AI systems will require us to make progress on scalable oversight: the problem of supervising systems that potentially outperform us on most skills relevant ... [Nov 2022] (Citations: 215; Topics: Alignment & RLHF)
G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model📑: Large language models (LLMs) have shown remarkable proficiency in human-level reasoning and generation capabilities, which encourages extensive research on their application in mathematical problem ... [Dec 2023] (Citations: 215; Topics: Reasoning in LLMs, RLVR & Process Reward Models, Multimodal LLMs)
Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study📑: Large language models (LLMs) are becoming attractive as few-shot reasoners to solve Natural Language (NL)-related tasks. [May 2023] (Citations: 214; Topics: Prompt Engineering & In-Context Learning, Evaluation of LLMs & Agents, Tabular Data & NL2SQL)
Uncertainty-guided Continual Learning with Bayesian Neural Networks📑: Continual learning aims to learn new tasks without forgetting previously learned ones. [Jun 2019] (Citations: 213; Topics: Continual Learning & Model Merging, GraphRAG & Knowledge Graphs, Scaling Laws)
Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning📑: Datasets are foundational to many breakthroughs in modern artificial intelligence. [Feb 2024] (Citations: 213; Topics: Instruction Tuning & SFT, Data for LLMs, Federated & Personalized AI)
CHESS: Contextual Harnessing for Efficient SQL Synthesis📑: Translating natural language questions into SQL queries, known as text-to-SQL, is a long-standing research problem. [May 2024] (Citations: 213; Topics: Tabular Data & NL2SQL, Efficient LLMs: Training & Inference, Context Engineering)
Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models📑: Recent advancements in large language models (LLMs) have led to significant breakthroughs in mathematical reasoning capabilities. [Oct 2024] (Citations: 213; Topics: Evaluation of LLMs & Agents, Reasoning in LLMs, RLVR & Process Reward Models)
A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?📑: As ChatGPT goes viral, generative AI (AIGC, a. [Mar 2023] (Citations: 212; Topics: LLM Overview & History)
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning📑: Inspired by the success of DeepSeek-R1, we explore the potential of rule-based reinforcement learning (RL) in large reasoning models. [Feb 2025] (Citations: 212; Topics: Reasoning in LLMs, RLVR & Process Reward Models, RLAIF & Constitutional AI)
Disentangling Length from Quality in Direct Preference Optimization📑: Reinforcement Learning from Human Feedback (RLHF) has been a crucial component in the recent success of Large Language Models. [Mar 2024] (Citations: 212; Topics: Alignment & RLHF, RLAIF & Constitutional AI, RLVR & Process Reward Models)
A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness📑: Large language models (LLMs) have demonstrated emergent abilities in text generation, question answering, and reasoning, facilitating various tasks and domains. [Nov 2024] (Citations: 212; Topics: Small Language Models, Scaling Laws, Reasoning in LLMs)
Effective Community Search over Large Spatial Graphs📑 (Citations: 211; Topics: GraphRAG & Knowledge Graphs)
Making LLaMA SEE and Draw with SEED Tokenizer📑: The great success of Large Language Models (LLMs) has expanded the potential of multimodality, contributing to the gradual evolution of General Artificial Intelligence (AGI). [Oct 2023] (Citations: 211; Topics: Multimodal LLMs, Federated & Personalized AI, Evaluation of LLMs & Agents)
@ CREPE: Can Vision-Language Foundation Models Reason Compositionally?📑: A fundamental characteristic common to both human vision and natural language is their compositional nature. [Dec 2022] (Citations: 211; Topics: Multimodal LLMs, LLM Overview & History)
Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints📑: Training large, deep neural networks to convergence can be prohibitively expensive. [Dec 2022] (Citations: 210; Topics: Mixture of Experts, GraphRAG & Knowledge Graphs, Embeddings & Vector Search)
OctoPack: Instruction Tuning Code Large Language Models📑: Finetuning large language models (LLMs) on instructions leads to vast performance improvements on natural language tasks. [Aug 2023] (Citations: 209; Topics: Instruction Tuning & SFT, LLMs for Code, PEFT & LoRA)
Aligning Modalities in Vision Large Language Models via Preference Fine-tuning📑: Instruction-following Vision Large Language Models (VLLMs) have achieved significant progress recently on a variety of tasks. [Feb 2024] (Citations: 209; Topics: Instruction Tuning & SFT, Alignment & RLHF, PEFT & LoRA)
AI-Generated Content (AIGC): A Survey📑: To address the challenges of digital intelligence in the digital economy, artificial intelligence-generated content (AIGC) has emerged. [Apr 2023] (Citations: 208; Topics: LLM Overview & History, Federated & Personalized AI)
Towards Continual Knowledge Learning of Language Models📑: Large Language Models (LMs) are known to encode world knowledge in their parameters as they pretrain on a vast amount of web corpus, which is often utilized for performing knowledge-dependent ... [Oct 2021] (Citations: 208; Topics: Continual Learning & Model Merging, PEFT & LoRA)
A Careful Examination of Large Language Model Performance on Grade School Arithmetic📑: Large language models (LLMs) have achieved impressive success on many benchmarks for mathematical reasoning. [May 2024] (Citations: 208; Topics: Evaluation of LLMs & Agents, Reasoning in LLMs, Multimodal LLMs)
A Review on Edge Large Language Models: Design, Execution, and Applications📑: Large language models (LLMs) have revolutionized natural language processing with their exceptional understanding, synthesizing, and reasoning capabilities. [Oct 2024] (Citations: 208; Topics: Reasoning in LLMs, RLVR & Process Reward Models)
Advancing LLM Reasoning Generalists with Preference Trees📑: We introduce Eurus, a suite of large language models (LLMs) optimized for reasoning. [Apr 2024] (Citations: 207; Topics: Reasoning in LLMs, Alignment & RLHF)
Can large language models replace humans in systematic reviews? Evaluating GPT‐4's efficacy in screening and extracting data from peer‐reviewed and grey literature in multiple languages📑: Systematic reviews are vital for guiding practice, research and policy, although they are often slow and labour‐intensive. [Oct 2023] (Citations: 207; Topics: GUI Agents, Data for LLMs, LLM Overview & History)
Fast Distributed Inference Serving for Large Language Models📑: Large language models (LLMs) power a new generation of interactive AI applications exemplified by ChatGPT. [May 2023] (Citations: 207; Topics: Efficient LLMs: Training & Inference, LLMOps & Model Serving, LLM Overview & History)
Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners📑: Large-scale pre-trained language models have contributed significantly to natural language processing by demonstrating remarkable abilities as few-shot learners. [Aug 2021] (Citations: 206; Topics: Prompt Engineering & In-Context Learning, Instruction Tuning & SFT)
MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use📑: Large language models (LLMs) have garnered significant attention due to their impressive natural language processing (NLP) capabilities. [Oct 2023] (Citations: 206; Topics: Evaluation of LLMs & Agents, LLM Architecture Innovations, Function Calling & Tool Use)
Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training📑: Prior work on Data-To-Text Generation, the task of converting knowledge graph (KG) triples into natural text, focused on domain-specific benchmark datasets. (Citations: 205; Topics: GraphRAG & Knowledge Graphs, Evaluation of LLMs & Agents, Data for LLMs)
Alibaba HPN: A Data Center Network for Large Language Model Training📑: This paper presents HPN, Alibaba Cloud's data center network for large language model (LLM) training. (Citations: 204; Topics: Data for LLMs)
OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models📑: To help the open-source community have a better understanding of Mixture-of-Experts (MoE) based large language models (LLMs), we train and release OpenMoE, a series of fully open-sourced and ... [Feb 2024] (Citations: 203; Topics: Mixture of Experts, LLM Overview & History)
Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents📑: Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning, yet their application in agentic, multi-step reasoning within interactive ... [Aug 2024] (Citations: 201; Topics: LLM Agents, Reasoning in LLMs, RLVR & Process Reward Models)
Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models📑: State-of-the-art neural language models can now be used to solve ad-hoc language tasks through zero-shot prompting without the need for supervised training. [Aug 2022] (Citations: 199; Topics: Prompt Engineering & In-Context Learning, Instruction Tuning & SFT)
Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese📑: The tremendous success of CLIP (Radford et al. [Nov 2022] (Citations: 198; Topics: Multimodal LLMs, Self-Supervised & Representation Learning)
Document-Level Machine Translation with Large Language Models📑: Large language models (LLMs) such as ChatGPT can produce coherent, cohesive, relevant, and fluent answers for various natural language processing (NLP) tasks. [Apr 2023] (Citations: 198; Topics: LLM Overview & History, Prompt Engineering & In-Context Learning, RLVR & Process Reward Models)
Does Prompt Formatting Have Any Impact on LLM Performance?📑: In the realm of Large Language Models (LLMs), prompt optimization is crucial for model performance. [Nov 2024] (Citations: 197; Topics: Prompt Engineering & In-Context Learning)
Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge📑: Large Language Models (LLMs) are rapidly surpassing human knowledge in many domains. [Jul 2024] (Citations: 197; Topics: Alignment & RLHF, Evaluation of LLMs & Agents, RLAIF & Constitutional AI)
Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects📑: Intelligent agents stand out as a potential path toward artificial general intelligence (AGI). [Jan 2024] (Citations: 196; Topics: LLM Agents, Federated & Personalized AI)
VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks📑: Embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering. [Oct 2024] (Citations: 196; Topics: Multimodal LLMs, Embeddings & Vector Search)
QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models📑: Recently years have witnessed a rapid development of large language models (LLMs). [Sep 2023] (Citations: 196; Topics: PEFT & LoRA, Efficient LLMs: Training & Inference)
MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning📑: While large language models (LLMs) equipped with techniques like chain-of-thought prompting have demonstrated impressive capabilities, they still fall short in their ability to reason robustly in ... [Oct 2023] (Citations: 196; Topics: Reasoning in LLMs, Prompt Engineering & In-Context Learning, Inference-Time Scaling & Test-Time Compute)
Compressing Context to Enhance Inference Efficiency of Large Language Models📑: Large language models (LLMs) achieved remarkable performance across various tasks. [Oct 2023] (Citations: 195; Topics: Efficient LLMs: Training & Inference)
Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning📑: In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning. [Jan 2023] (Citations: 194; Topics: Prompt Engineering & In-Context Learning, Inference-Time Scaling & Test-Time Compute, Efficient LLMs: Training & Inference)
Large Language Models for Robotics: Opportunities, Challenges, and Perspectives📑: Large language models (LLMs) have undergone significant expansion and have been increasingly integrated across various domains. [Jan 2024] (Citations: 193; Topics: LLM for Robotics & Embodied AI)
Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering📑: Large Language Models (LLMs) are capable of performing zero-shot closed-book question answering tasks, based on their internal knowledge stored in parameters during pre-training. [Jun 2023] (Citations: 193; Topics: GraphRAG & Knowledge Graphs, Prompt Engineering & In-Context Learning, Tabular Data & NL2SQL)
TPTU: Task Planning and Tool Usage of Large Language Model-based AI Agents📑 (Citations: 192; Topics: LLM Agents, Function Calling & Tool Use)
Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs📑: Recent advancements in multimodal large language models (MLLMs) have been noteworthy, yet, these general-domain MLLMs often fall short in their ability to comprehend and interact effectively with ... [Apr 2024] (Citations: 192; Topics: Multimodal LLMs)
Give us the Facts: Enhancing Large Language Models With Knowledge Graphs for Fact-Aware Language Modeling📑: Recently, ChatGPT, a representative large language model (LLM), has gained considerable attention. [Jun 2023] (Citations: 192; Topics: GraphRAG & Knowledge Graphs, LLM Architecture Innovations, LLM Overview & History)
MART: Improving LLM Safety with Multi-round Automatic Red-Teaming📑: Red-teaming is a common practice for mitigating unsafe behaviors in Large Language Models (LLMs), which involves thoroughly assessing LLMs to identify potential flaws and addressing them with ... [Nov 2023] (Citations: 192; Topics: Trustworthy & Secure LLMs)
LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B📑: AI developers often apply safety alignment procedures to prevent the misuse of their AI systems. [Oct 2023] (Citations: 192; Topics: PEFT & LoRA, Alignment & RLHF, Efficient LLMs: Training & Inference)
Self-Supervised Learning for Few-Shot Medical Image Segmentation📑: Fully-supervised deep learning segmentation models are inflexible when encountering new unseen semantic classes and their fine-tuning often requires significant amounts of annotated data. (Citations: 190; Topics: Self-Supervised & Representation Learning, Prompt Engineering & In-Context Learning, Multimodal LLMs)
Guiding Instruction-based Image Editing via Multimodal Large Language Models📑: Instruction-based image editing improves the controllability and flexibility of image manipulation via natural commands without elaborate descriptions or regional masks. [Sep 2023] (Citations: 190; Topics: Multimodal LLMs, Instruction Tuning & SFT)
Repository-Level Prompt Generation for Large Language Models of Code📑: With the success of large language models (LLMs) of code and their use as code assistants (e. [Jun 2022] (Citations: 189; Topics: LLMs for Code, Prompt Engineering & In-Context Learning)
Recursive Introspection: Teaching Language Model Agents How to Self-Improve📑: A central piece in enabling intelligent agentic behavior in foundation models is to make them capable of introspecting upon their behavior, reasoning, and correcting their mistakes as more ... [Jul 2024] (Citations: 189; Topics: LLM Agents, LLM Overview & History, Reasoning in LLMs)
Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints📑: The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but concurrently amplify safety concerns, such as potential misuse of AI systems ... [Sep 2023] (Citations: 189; Topics: Alignment & RLHF, Trustworthy & Secure LLMs, Federated & Personalized AI)
Self-Supervised Learning for Videos: A Survey📑: The remarkable success of deep learning in various domains relies on the availability of large-scale annotated datasets. [Jul 2022] (Citations: 188; Topics: Self-Supervised & Representation Learning, Multimodal LLMs, Data for LLMs)
Evolutionary Computation in the Era of Large Language Model: Survey and Roadmap📑: Large language models (LLMs) have not only revolutionized natural language processing but also extended their prowess to various domains, marking a significant stride toward artificial general ... [Jan 2024] (Citations: 188; Topics: LLM Overview & History, Federated & Personalized AI)
Power Efficient Traffic Grooming in Optical WDM Networks📑 (Citations: 187; Topics: Efficient LLMs: Training & Inference)
Selective Structured State-Spaces for Long-Form Video Understanding📑: Effective modeling of complex spatiotemporal dependencies in long-form videos remains an open problem. [Mar 2023] (Citations: 187; Topics: Multimodal LLMs, LLM Architecture Innovations)
Overcoming Catastrophic Forgetting in Graph Neural Networks with Experience Replay📑: Graph Neural Networks (GNNs) have recently received significant research attention due to their superior performance on a variety of graph-related learning tasks. (Citations: 187; Topics: Continual Learning & Model Merging, LLM Architecture Innovations, GraphRAG & Knowledge Graphs)
The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4📑: In recent years, groundbreaking advancements in natural language processing have culminated in the emergence of powerful large language models (LLMs), which have showcased remarkable capabilities ... [Nov 2023] (Citations: 186; Topics: LLMs for Healthcare & Science)
MuLan: A Joint Embedding of Music Audio and Natural Language📑: Music tagging and content-based retrieval systems have traditionally been constructed using pre-defined ontologies covering a rigid set of music attributes or text queries. [Aug 2022] (Citations: 185; Topics: Embeddings & Vector Search, Multimodal LLMs, Retrieval-Augmented Generation (RAG))
Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking📑: Reward models play a key role in aligning language model applications towards human preferences. [Dec 2023] (Citations: 184; Topics: Alignment & RLHF, RLAIF & Constitutional AI, RLVR & Process Reward Models)
Evaluating Open-Domain Question Answering in the Era of Large Language Models📑: Lexical matching remains the de facto evaluation method for open-domain question answering (QA). [May 2023] (Citations: 183; Topics: Evaluation of LLMs & Agents, Tabular Data & NL2SQL, Retrieval-Augmented Generation (RAG))
Large Language Models Can Learn Temporal Reasoning📑: While large language models (LLMs) have demonstrated remarkable reasoning capabilities, they are not without their flaws and inaccuracies. [Jan 2024] (Citations: 183; Topics: Reasoning in LLMs)
AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs📑: As large language models (LLMs) become increasingly prevalent and integrated into autonomous systems, ensuring their safety is imperative. [Apr 2024] (Citations: 183; Topics: Trustworthy & Secure LLMs, LLM Agents, Efficient LLMs: Training & Inference)
14 examples of how LLMs can transform materials science and chemistry: a reflection on a large language model hackathon📑: Large-language models (LLMs) such as GPT-4 caught the interest of many scientists. [Jun 2023] (Citations: 182; Topics: LLMs for Healthcare & Science)
Convolutional Bypasses Are Better Vision Transformer Adapters📑: The pretrain-then-finetune paradigm has been widely adopted in computer vision. [Jul 2022] (Citations: 182; Topics: PEFT & LoRA)
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding📑: Document understanding refers to automatically extract, analyze and comprehend information from various types of digital documents, such as a web page. [Jul 2023] (Citations: 182; Topics: Multimodal LLMs)
A Survey of Text Representation and Embedding Techniques in NLP📑: Natural Language Processing (NLP) is a research field where a language in consideration is processed to understand its syntactic, semantic, and sentimental aspects. (Citations: 181; Topics: Embeddings & Vector Search, LLM Overview & History)
Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering📑: Large Language Models (LLMs) are capable of performing zero-shot closed-book question answering tasks, based on their internal knowledge stored in parameters during pre-training. (Citations: 181; Topics: GraphRAG & Knowledge Graphs, Prompt Engineering & In-Context Learning, Tabular Data & NL2SQL)
A Mutual Information Maximization Perspective of Language Representation Learning📑: We show state-of-the-art word representation learning methods maximize an objective function that is a lower bound on the mutual information between different parts of a word sequence (i. [Oct 2019] (Citations: 180; Topics: Self-Supervised & Representation Learning, LLM Architecture Innovations, PEFT & LoRA)
Reducing hallucination in structured outputs via Retrieval-Augmented Generation📑: A common and fundamental limitation of Generative AI (GenAI) is its propensity to hallucinate. [Apr 2024] (Citations: 180; Topics: Retrieval-Augmented Generation (RAG), Hallucination in LLMs, Context Engineering)
Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation📑: Large language models (large LMs) are susceptible to producing text that contains hallucinated content. [May 2023] (Citations: 180; Topics: Hallucination in LLMs, Evaluation of LLMs & Agents, Instruction Tuning & SFT)
Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces📑: Attention mechanisms have been widely used to capture long-range dependencies among nodes in Graph Transformers. [Feb 2024] (Citations: 180; Topics: LLM Architecture Innovations, GraphRAG & Knowledge Graphs, Efficient LLMs: Training & Inference)
Differential Privacy for Industrial Internet of Things: Opportunities, Applications, and Challenges📑: The development of Internet of Things (IoT) brings new changes to various fields. [Jan 2021] (Citations: 179; Topics: Trustworthy & Secure LLMs, LLM Overview & History)
Accelerating LLM Inference with Staged Speculative Decoding📑: Recent advances with large language models (LLM) illustrate their diverse capabilities. [Aug 2023] (Citations: 179; Topics: Efficient LLMs: Training & Inference)
Drive as You Speak: Enabling Human-Like Interaction with Large Language Models in Autonomous Vehicles📑: The future of autonomous vehicles lies in the convergence of human-centric design and advanced AI capabilities. [Sep 2023] (Citations: 178; Topics: LLM Agents)
LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning📑: Fine-tuning large language models (LLMs) is crucial for improving their performance on downstream tasks, but full-parameter fine-tuning (Full-FT) is computationally expensive and memory-intensive. [Aug 2023] (Citations: 177; Topics: PEFT & LoRA, Efficient LLMs: Training & Inference, LLM Memory & Personalization)
Internet-augmented language models through few-shot prompting for open-domain question answering📑: In this work, we aim to capitalize on the unique few-shot capabilities of large-scale language models (LSLMs) to overcome some of their challenges with respect to grounding to factual and up-to-date ... [Mar 2022] (Citations: 177; Topics: Prompt Engineering & In-Context Learning, Tabular Data & NL2SQL, Retrieval-Augmented Generation (RAG))
VICRegL: Self-Supervised Learning of Local Visual Features📑: Most recent self-supervised methods for learning image representations focus on either producing a global feature with invariance properties, or producing a set of local features. [Oct 2022] (Citations: 177; Topics: Self-Supervised & Representation Learning, Multimodal LLMs, PEFT & LoRA)
Jointly Learning to Parse and Perceive: Connecting Natural Language to the Physical World📑: This paper introduces Logical Semantics with Perception (LSP), a model for grounded language acquisition that learns to map natural language statements to their referents in a physical environment. (Citations: 176; Topics: LLM for Robotics & Embodied AI)
Emergent autonomous scientific research capabilities of large language models📑: Transformer-based large language models are rapidly advancing in the field of machine learning research, with applications spanning natural language, biology, chemistry, and computer programming. [Apr 2023] (Citations: 176; Topics: LLMs for Healthcare & Science, LLM Agents, Scaling Laws)
Understanding the Benefits and Challenges of Using Large Language Model-based Conversational Agents for Mental Well-being Support📑: Conversational agents powered by large language models (LLM) have increasingly been utilized in the realm of mental well-being support. [Jul 2023] (Citations: 176; Topics: LLM Agents, LLM Memory & Personalization)
Overcoming Catastrophic Forgetting in Graph Neural Networks📑: Catastrophic forgetting refers to the tendency that a neural network ``forgets'' the previous learned knowledge upon learning new tasks. [Dec 2020] (Citations: 176; Topics: Continual Learning & Model Merging, GraphRAG & Knowledge Graphs, Scaling Laws)
Teaching Large Language Models to Reason with Reinforcement Learning📑: Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. [Mar 2024] (Citations: 175; Topics: Alignment & RLHF, RLAIF & Constitutional AI, RLVR & Process Reward Models)
Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step by Step📑: Large language models (LLMs) are leading significant progress in code generation. [Feb 2024] (Citations: 175; Topics: LLMs for Code, RLVR & Process Reward Models, Reasoning in LLMs)
Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods📑: Self-Supervised Learning (SSL) surmises that inputs and pairwise positive relationships are enough to learn meaningful representations. [May 2022] (Citations: 173; Topics: Self-Supervised & Representation Learning, Embeddings & Vector Search, PEFT & LoRA)
A simple solution for model comparison in bold imaging: the special case of reward prediction error and reward outcomes📑: Conventional neuroimaging techniques provide information about condition-related changes of the BOLD (blood-oxygen-level dependent) signal, indicating only where and when the underlying cognitive ... (Citations: 172; Topics: RLVR & Process Reward Models)
LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Model📑: In this paper, we introduce LLaVA-φ (LLaVA-Phi), an efficient multi-modal assistant that harnesses the power of the recently advanced small language model, Phi-2, to facilitate multi-modal dialogues. [Jan 2024] (Citations: 172; Topics: Small Language Models, Efficient LLMs: Training & Inference)
On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence📑: Large pre-trained models, also known as foundation models (FMs), are trained in a task-agnostic manner on large-scale data and can be adapted to a wide range of downstream tasks by fine-tuning ... [Apr 2023] (Citations: 171; Topics: LLM Overview & History, Data for LLMs, Instruction Tuning & SFT)
Solo-learn: A Library of Self-supervised Methods for Visual Representation Learning📑: This paper presents solo-learn, a library of self-supervised methods for visual representation learning. [Aug 2021] (Citations: 171; Topics: Self-Supervised & Representation Learning, PEFT & LoRA, Instruction Tuning & SFT)
A Survey of AI-Generated Content (AIGC)📑: Recently, Artificial Intelligence Generated Content (AIGC) has gained significant attention from society, especially with the rise of Generative AI (GAI) techniques such as ChatGPT, GPT-4 [165] ... (Citations: 171; Topics: LLM Overview & History, LLM Architecture Innovations, Federated & Personalized AI)
GPT-RE: In-context Learning for Relation Extraction using Large Language Models📑: In spite of the potential for ground-breaking achievements offered by large language models (LLMs) (e. [May 2023] (Citations: 170; Topics: Prompt Engineering & In-Context Learning)
Optimization of hepatological clinical guidelines interpretation by large language models: a retrieval augmented generation-based framework📑: Large language models (LLMs) can potentially transform healthcare, particularly in providing the right information to the right provider at the right time in the hospital workflow. (Citations: 168; Topics: Retrieval-Augmented Generation (RAG), LLMs for Healthcare & Science, Context Engineering)
Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation📑: We introduce a novel graph-based Retrieval-Augmented Generation (RAG) framework specifically designed for the medical domain, called \textbf{MedGraphRAG}, aimed at enhancing Large Language Model ... [Aug 2024] (Citations: 166; Topics: GraphRAG & Knowledge Graphs, Retrieval-Augmented Generation (RAG), LLMs for Healthcare & Science)
Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning📑: Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on learned prompt vectors, has emerged as a promising approach for efficiently adapting large language models ... [Mar 2023] (Citations: 164; Topics: PEFT & LoRA, Prompt Engineering & In-Context Learning, Efficient LLMs: Training & Inference)
Interactive AI With Retrieval-Augmented Generation for Next Generation Networking📑: With the advance of artificial intelligence (AI), the concept of interactive AI (IAI) has been introduced, which can interactively understand and respond not only to human user input but also to ... [Jan 2024] (Citations: 164; Topics: Retrieval-Augmented Generation (RAG), Context Engineering, Federated & Personalized AI)
Dense Depth Estimation in Monocular Endoscopy with Self-supervised Learning Methods📑: We present a self-supervised approach to training convolutional neural networks for dense depth estimation from monocular endoscopy data without a priori modeling of anatomy or shading. [Feb 2019] (Citations: 162; Topics: Self-Supervised & Representation Learning, Data for LLMs, Scaling Laws)
Are Emergent Abilities in Large Language Models just In-Context Learning?📑: Large language models, comprising billions of parameters and pre-trained on extensive web-scale corpora, have been claimed to acquire certain capabilities without having been specifically trained on ... [Sep 2023] (Citations: 158; Topics: Prompt Engineering & In-Context Learning, Scaling Laws, PEFT & LoRA)
One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era📑: OpenAI has recently released GPT-4 [Apr 2023] (Citations: 157; Topics: LLM Overview & History, Small Language Models, Reasoning in LLMs)

FilesExpand file tree

x_llm_papers.md

Latest commit

History

x_llm_papers.md

File metadata and controls

LLM Landscape Papers (Citation ≥ 150)

Topic Coverage

Papers