Add Jiang report

Author: cakiki

lichess.bib

@@ -527,6 +527,15 @@ @article{jenner:2024:evidence-lookahead-chess-neural-network
   eprint        = {2406.00877},
 }
 
+@misc{jiang:2023:building-natural-language-chess-engine-pretraining-instruction-finetunine,
+  title         = {Building a Natural Language Chess Engine with Pretraining and Instruction Fine-Tuning},
+  author        = {Bowen Jiang},
+  year          = {2023},
+  url           = {https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1234/final-reports/final-report-169466939.pdf},
+  note          = {Stanford CS224N Custom Project, Winter 2023 (https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1234/project.html)},
+  abstract      = {Although pretrained large language models (LLMs) can generate convincing natural language about games like chess, they lack positional and contextual knowledge and as such are poor game-playing agents. In this project, I utilize language pretaining; instruction fine-tuning, an additional training regimen with chess-specific tasks presented in natural language; and chain-of-thought prompting, a natural language description of problem reasoning prepended to the answer of a problem, to improve the performance of LLMs at chess move generation (validity/legality and quality of moves). I show that fine-tuned GPT-2-XL, a 1.5B parameter LLM, performs favorably well at move generation compared to ChatGPT with few-shot learning; I also validate the additional benefits of chain-of-thought prompting compared to plain prompts in ChatGPT while highlighting tradeoffs between the quality of natural language and the quality of chess when more verbose prompts are used in the smaller GPT-2-XL.},
+}
+
 @misc{kapla:2025:generalized-multi-linear-models-dimension-reduction-tensor-valued-predictors,
   title         = {Generalized Multi-Linear Models for Sufficient Dimension Reduction on Tensor Valued Predictors},
   author        = {Daniel Kapla and Efstathia Bura},