Skip to content

Commit 23a87a7

Browse files
minor rendering fixes to publications and research proposals
1 parent 333ec0b commit 23a87a7

File tree

2 files changed

+38
-36
lines changed

2 files changed

+38
-36
lines changed

content/publications.md

Lines changed: 31 additions & 29 deletions
Original file line numberDiff line numberDiff line change
@@ -9,39 +9,39 @@ description: "Current list of publications of our group."
99
## Highlights
1010

1111
**Is It Worth Using LLMs for Unfair Clause Detection in Terms of Service?**\
12-
Marco Panarelli, Andrea Galassi, Francesca Lagioia, Rūta Liepiņa, Marco Lippi, Przemysław Pałka, Giovanni Sartor\
13-
20th International Conference on Artificial Intelligence and Law (ICAIL), pp. 139-149, 2025\
14-
:trophy: Awarded the "Peter Jackson" Award for Best Innovative Application Paper\
12+
Marco Panarelli, Andrea Galassi, Francesca Lagioia, Rūta Liepiņa, Marco Lippi, Przemysław Pałka, Giovanni Sartor.\
13+
20th International Conference on Artificial Intelligence and Law (ICAIL), pp. 139-149, 2025.\
14+
:trophy: Awarded the "Peter Jackson" Award for Best Innovative Application Paper.\
1515
[DOI](https://dl.acm.org/doi/10.1145/3769126.3769218)
1616
| [PDF](https://dl.acm.org/doi/pdf/10.1145/3769126.3769218)
1717

1818
**Promoting the Responsible Development of Speech Datasets for Mental Health and Neurological Disorders Research**\
19-
Eleonora Mancini, Ana Tanevska, Andrea Galassi, Alessio Galatolo, Federico Ruggeri, Paolo Torroni\
20-
Journal of Artificial Intelligence Research (JAIR), 82:937-972, 2025\
19+
Eleonora Mancini, Ana Tanevska, Andrea Galassi, Alessio Galatolo, Federico Ruggeri, Paolo Torroni.\
20+
Journal of Artificial Intelligence Research (JAIR), 82:937-972, 2025.\
2121
[DOI](https://doi.org/10.1613/jair.1.16406)
2222
| [PDF](https://jair.org/index.php/jair/article/view/16406/27137)
2323

2424
**Unfair clause detection in terms of service across multiple languages**\
25-
Andrea Galassi, Francesca Lagioia, Agnieszka Jabłonowska, and Marco Lippi\
26-
Artificial Intelligence and Law, 2024\
25+
Andrea Galassi, Francesca Lagioia, Agnieszka Jabłonowska, and Marco Lippi.\
26+
Artificial Intelligence and Law, 2024.\
2727
[DOI](https://doi.org/10.1007/s10506-024-09398-7)
2828
| [PDF](https://link.springer.com/content/pdf/10.1007/s10506-024-09398-7.pdf)
2929

3030
**Multimodal Fallacy Classification in Political Debates**\
31-
Eleonora Mancini, Federico Ruggeri, Paolo Torroni\
32-
18th Conference of the European Chapter of the Association for Computational Linguistics (EACL), pp. 170–178, 2024\
31+
Eleonora Mancini, Federico Ruggeri, Paolo Torroni.\
32+
18th Conference of the European Chapter of the Association for Computational Linguistics (EACL), pp. 170–178, 2024.\
3333
[DOI](https://doi.org/10.18653/v1/2024.eacl-short.16)
3434
| [PDF](https://aclanthology.org/2024.eacl-short.16.pdf)
3535

3636
**Attention in Natural Language Processing**\
37-
Andrea Galassi, Marco Lippi, and Paolo Torroni\
38-
IEEE Transactions on Neural Networks and Learning Systems 32(10), pp 4291-4308, 2021\
37+
Andrea Galassi, Marco Lippi, and Paolo Torroni.\
38+
IEEE Transactions on Neural Networks and Learning Systems 32(10), pp 4291-4308, 2021.\
3939
[DOI](https://doi.org/10.1109/TNNLS.2020.3019893)
4040
| [PDF](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9194070)
4141

4242
**MARGOT: A web server for argumentation mining**\
43-
Marco Lippi and Paolo Torroni\
44-
Expert Systems with Applications, 65:292-303, 2016\
43+
Marco Lippi and Paolo Torroni.\
44+
Expert Systems with Applications, 65:292-303, 2016.\
4545
[DOI](https://doi.org/10.1016/j.eswa.2016.08.050)
4646

4747
------
@@ -151,7 +151,7 @@ Giulia Grundler, Mariaceleste Musicco, Andrea Galassi, Francesca Lagioia, Rūta
151151
28th European Conference on Artificial Intelligence (ECAI), pp. 4594-4602, 2025\
152152
[DOI](https://doi.org/10.3233/FAIA251362)
153153

154-
**Untangling Hate Speech Definitions: A Semantic Componential Analysis Across Cultures and Domains.**\
154+
**Untangling Hate Speech Definitions: A Semantic Componential Analysis Across Cultures and Domains.**\
155155
Katerina Korre, Arianna Muti, Federico Ruggeri, and Alberto Barrón-Cedeño. 2025.\
156156
In Findings of the Association for Computational Linguistics: NAACL 2025, pages 3184–3198, Albuquerque, New Mexico. Association for Computational Linguistics.\
157157
[DOI](https://doi.org/10.18653/v1/2025.findings-naacl.175)
@@ -189,8 +189,8 @@ In Proceedings of the 2024 Joint International Conference on Computational Lingu
189189
| [Anthology](https://aclanthology.org/2024.lrec-main.1112)
190190

191191
**The CLEF-2024 CheckThat! Lab: Check-Worthiness, Subjectivity, Persuasion, Roles, Authorities, and Adversarial Robustness**\
192-
Alberto Barrón-Cedeño, Firoj Alam, Tanmoy Chakraborty, Tamer Elsayed, Preslav Nakov, Piotr Przybyła, Julia Maria Struß, Fatima Haouari, Maram Hasanain, Federico Ruggeri, Xingyi Song, Reem Suwaileh\\
193-
46th European Conference on Information Retrieval (ECIR), 2024\
192+
Alberto Barrón-Cedeño, Firoj Alam, Tanmoy Chakraborty, Tamer Elsayed, Preslav Nakov, Piotr Przybyła, Julia Maria Struß, Fatima Haouari, Maram Hasanain, Federico Ruggeri, Xingyi Song, Reem Suwaileh.\
193+
46th European Conference on Information Retrieval (ECIR), 2024.\
194194
[DOI](https://doi.org/10.1007/978-3-031-56069-9_62)
195195

196196
**TWOLAR: a TWO-step LLM-Augmented distillation method for passage Reranking**\
@@ -300,15 +300,17 @@ Marco Lippi and Paolo Torroni\
300300
## Workshops
301301

302302
### 2025
303-
Luca Moroni, Gianmarco Pappacoda, Edoardo Barba, Simone Conia, Andrea Galassi, Bernardo Magnini, Roberto Navigli, Paolo Torroni, and Roberto Zanoli. 2025.
304-
Sustainable Italian LLM Evaluation: Community Perspectives and Methodological Guidelines.
305-
In Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025), pages 747–759, Cagliari, Italy. CEUR Workshop Proceedings.
303+
304+
**Sustainable Italian LLM Evaluation: Community Perspectives and Methodological Guidelines**\
305+
Luca Moroni, Gianmarco Pappacoda, Edoardo Barba, Simone Conia, Andrea Galassi, Bernardo Magnini, Roberto Navigli, Paolo Torroni, and Roberto Zanoli. 2025.\
306+
In Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025), pages 747–759, Cagliari, Italy. CEUR Workshop Proceedings.\
306307
[PDF](https://aclanthology.org/2025.clicit-1.71.pdf)
307308
| [Anthology](https://aclanthology.org/2025.clicit-1.71/)
308309

309-
**Nicolò Donati, Paolo Torroni, and Giuseppe Savino. 2025.**\
310-
Do Large Language Models understand how to be judges?.\
311-
In Proceedings of the 2nd LUHME Workshop, pages 85–102, Bologna, Italy. UP - Universidade do Porto (https://doi.org/10.21747/978-989-9193-73-4/lan2), LIACC - Laboratório de Inteligência Artificial e Ciência de Computadores da Universidade do Porto, CLUP - Centro de Linguística da Universidade do Porto, UEF - The University of Eastern Finland and UAH - Universidad de Alcalá.\
310+
311+
**Do Large Language Models understand how to be judges?**\
312+
Nicolò Donati, Paolo Torroni, and Giuseppe Savino. 2025.\
313+
In Proceedings of the 2nd LUHME Workshop, pages 85–102, Bologna, Italy. UP - Universidade do Porto, LIACC - Laboratório de Inteligência Artificial e Ciência de Computadores da Universidade do Porto, CLUP - Centro de Linguística da Universidade do Porto, UEF - The University of Eastern Finland and UAH - Universidad de Alcalá.\
312314
[PDF](https://aclanthology.org/2025.luhme-1.9.pdf)
313315
| [Anthology](https://aclanthology.org/2025.luhme-1.9/)
314316

@@ -318,14 +320,14 @@ Eleonora Mancini, Francesco Paissan, Paolo Torroni, Mirco Ravanelli, Cem Subakan
318320
[PDF](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=11011035)
319321

320322
**Overview of MM-ArgFallacy2025 on Multimodal Argumentative Fallacy Detection and Classification in Political Debates.**\
321-
Eleonora Mancini, Federico Ruggeri, Serena Villata, and Paolo Torroni. 2025.\
322-
In Proceedings of the 12th Argument mining Workshop, pages 358–368, Vienna, Austria. Association for Computational Linguistics.\
323+
Eleonora Mancini, Federico Ruggeri, Serena Villata, and Paolo Torroni.\
324+
In Proceedings of the 12th Argument mining Workshop, pages 358–368, Vienna, Austria. Association for Computational Linguistics, 2025.\
323325
[DOI](https://doi.org/10.18653/v1/2025.argmining-1.35)
324326
| [PDF](https://aclanthology.org/2025.argmining-1.35.pdf)
325327

326-
Overview of the CLEF-2025 CheckThat! Lab: Subjectivity, Fact-Checking, Claim Normalization, and Retrieval\
327-
Firoj Alam, Julia Maria Struß, Tanmoy Chakraborty, Stefan Dietze, Salim Hafid, Katerina Korre, Arianna Muti, Preslav Nakov, Federico Ruggeri, Sebastian Schellhammer, Vinay Setty, Megha Sundriyal, Konstantin Todorov & V. Venktesh\
328-
Conference and Labs of the Evaluation Forum (CLEF), 2025.\\
328+
**Overview of the CLEF-2025 CheckThat! Lab: Subjectivity, Fact-Checking, Claim Normalization, and Retrieval**\
329+
Firoj Alam, Julia Maria Struß, Tanmoy Chakraborty, Stefan Dietze, Salim Hafid, Katerina Korre, Arianna Muti, Preslav Nakov, Federico Ruggeri, Sebastian Schellhammer, Vinay Setty, Megha Sundriyal, Konstantin Todorov & V. Venktesh.\
330+
Conference and Labs of the Evaluation Forum (CLEF), 2025.\
329331
[DOI](https://doi.org/10.1007/978-3-032-04354-2_13)
330332

331333
**Dynamic Demonstrations Selection for Few-Shot Legal Argument Mining**\
@@ -334,7 +336,7 @@ AMELR: First Argument Mining and Empirical Legal Research Workshop\
334336
[PDF](https://ceur-ws.org/Vol-4089/paper2.pdf)
335337

336338
### 2024
337-
A Grice-ful Examination of Offensive Language: Using NLP Methods to Assess the Co-operative Principle.\
339+
**A Grice-ful Examination of Offensive Language: Using NLP Methods to Assess the Co-operative Principle.**\
338340
Katerina Korre, Federico Ruggeri, and Alberto Barrón-Cedeño. 2024.\
339341
In Proceedings of the 1st LUHME Workshop, pages 12–19, Santiago de Compostela, Spain. CLUP, Centro de Linguística da Universidade do Porto FLUP - Faculdade de Letras da Universidade do Porto.\
340342
[PDF](https://aclanthology.org/2024.luhme-1.2.pdf)
@@ -388,7 +390,7 @@ Francesco Antici, Luca Bolognini, Matteo Antonio Inajetovic, Bogdan Ivasiuk, And
388390
12th Conference and Labs of the Evaluation Forum (CLEF), pp. 40–52, 2021\
389391
[DOI](https://doi.org/10.1007/978-3-030-85251-1_4)
390392

391-
**Detecting Arguments in CJEU Decisions on Fiscal State Aid.**\
393+
**Detecting Arguments in CJEU Decisions on Fiscal State Aid.**\
392394
Giulia Grundler, Piera Santin, Andrea Galassi, Federico Galli, Francesco Godano, Francesca Lagioia, Elena Palmieri, Federico Ruggeri, Giovanni Sartor, and Paolo Torroni. 2022.\
393395
In Proceedings of the 9th Workshop on Argument Mining, pages 143–157, Online and in Gyeongju, Republic of Korea. International Conference on Computational Linguistics.\
394396
[PDF](https://aclanthology.org/2022.argmining-1.14.pdf)

content/research/proposals/index.md

Lines changed: 7 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -34,7 +34,7 @@ Few existing corpora both offer argument annotation layers and speech data regar
3434

3535
**References:**
3636

37-
**MAMKit: A Comprehensive Multimodal Argument Mining Toolkit.**\
37+
**MAMKit: A Comprehensive Multimodal Argument Mining Toolkit.**\
3838
Eleonora Mancini, Federico Ruggeri, Stefano Colamonaco, Andrea Zecca, Samuele Marro, and Paolo Torroni. 2024.\
3939
In Proceedings of the 11th Workshop on Argument Mining (ArgMining 2024), pages 69–82, Bangkok, Thailand. Association for Computational Linguistics.\
4040
[DOI](https://doi.org/10.18653/v1/2024.argmining-1.7)
@@ -87,7 +87,7 @@ We are in close contact with teams of legal experts who can provide their expert
8787

8888
### - Transformers and LLMs for the detection and classification of unfair clauses -
8989

90-
**Description:**\
90+
**Description:**
9191
For several years, we have been working on tools for the automatic detection of unfair clauses in Terms of Services and Privacy Policies documents in the English language (see CLAUDETTE and PRIMA [Projects page](\projects)).
9292
We have already conducted several studies on this topic, and we are interested in applying new effective methods and techniques.
9393
Right now, we are focused on LLMs, but we are also interested in alternative techniques.
@@ -149,9 +149,9 @@ However, properly integrating this type of information is particularly challengi
149149
The standard approach for training a machine learning model on a task is to provide an annotated dataset $(\mathcal{X}, \mathcal{Y})$.
150150
The dataset is built by providing unlabeled data $\mathcal{X}$ to a group of annotators previously trained on a set of annotation guidelines $\mathcal{G}$.
151151
Annotators label data $\mathcal{X}$ via a given class set $\mathcal{C}$.
152-
The main issue of this approach is that annotators define the mapping from data \mathcal{X} to the class set \mathcal{C} via the guidelines \mathcal{G}, while machine learning models are trained to learn the same mapping without guidelines \mathcal{G}.
153-
Consequently, these models can learn any kind of mapping from \mathcal{X} to \mathcal{C} that better fits given data.
154-
Our idea is to directly provide guidelines \mathcal{G} to models without any access to class labels during training.
152+
The main issue of this approach is that annotators define the mapping from data $\mathcal{X}$ to the class set $\mathcal{C}$ via the guidelines $\mathcal{G}$, while machine learning models are trained to learn the same mapping without guidelines $\mathcal{G}$.
153+
Consequently, these models can learn any kind of mapping from $\mathcal{X}$ to $\mathcal{C}$ that better fits given data.
154+
Our idea is to directly provide guidelines $\mathcal{G}$ to models without any access to class labels during training.
155155

156156
**Contact:** [Federico Ruggeri](mailto:federico.ruggeri6@unibo.it)
157157

@@ -173,7 +173,7 @@ Our aim is to evaluate how machine learning model are affected by different defi
173173

174174
**References:**
175175

176-
**Untangling Hate Speech Definitions: A Semantic Componential Analysis Across Cultures and Domains.**\
176+
**Untangling Hate Speech Definitions: A Semantic Componential Analysis Across Cultures and Domains.**\
177177
Katerina Korre, Arianna Muti, Federico Ruggeri, and Alberto Barrón-Cedeño. 2025.\
178178
In Findings of the Association for Computational Linguistics: NAACL 2025, pages 3184–3198, Albuquerque, New Mexico. Association for Computational Linguistics.\
179179
[DOI](https://doi.org/10.18653/v1/2025.findings-naacl.175)
@@ -188,7 +188,7 @@ We are mainly focused on interpretability by design in text classification.
188188

189189
Current topics of interest:
190190

191-
**Selective Rationalization:**\
191+
**Selective Rationalization:**\
192192
The process of learning by providing highlights as explanations is denoted as selective rationalization.
193193
Highlights are a subset of input texts meant to be interpretable by a user and faithfully describe the inference process of a classification model.
194194
A popular architecture for selective rationalization is the Select-then-Predict Pipeline (SPP): a generator selects the rationale to be fed to a predictor.

0 commit comments

Comments
 (0)