General Observations
- The Conference was very large, receiving 70% more submissions than ACL 2024:
- What already dawned in previous major CL/NLP conferences has now become clear: Chinese researchers are dominating the field:
- The LLM hype and excitement have given way to an LLM exhaustion and nausea (67% of Papers have “LLM’’ in title): Prompting techniques, challenge datasets have become so elaborate and domain-specific that it becomes very difficult to see how any of the results could apply to one’s own research (or, of course, still hold in two weeks’ time).
Paper Highlights
- Quan, Valentino, Dennis, et al. (2025): Applies a number of really smart steps to impressively improve neuro-symbolic NLI performance.
- Feger, Boland, and Dietze (n.d.): Suggests that LLMs are rather memorizing spurious aspects of datasets than learning abstract, general concepts when it comes to Argument Mining.
- Resnik (2025): A great start for ACL’s new position paper category: Large Language Models are Biased because they are large language models:
Full List of Papers that I Found relevant For My Research
Neuro-Symbolic Methods in Argumentation/NLI
NLI
Argumentation
- Counter-argument generation with facts: Yeginbergen, Oronoz, and Agerri (2025)
- Instruction fine-tuning for computational argumentation: Stahl et al. (2025)
- Mining complex argument patterns (new dataset): Ruiz-Dolz, Kikteva, and Lawrence (2025)
- Rational pragmatics: Spinoso-Di Piano et al. (2025)
- Open Argument mining framework: Gemechu et al. (2025)
- Can large language models understand argument schemes? Bezou-Vrakatseli, Cocarascu, and Modgil (2025)
- Disputool 3.0: Fallacy detection in arguments: Goffredo et al. (2025)
LLM Handling
- Prompt programming language: Dong et al. (2025)
For Research
- Search and summarize papers: He et al. (2025)
Not really relevant to my projects, but particularly exciting
- Word-sense induction remains unsolved: Mosolova, Candito, and Ramisch (2025)
- Stochastic chameleons: Cheng et al. (2025)
- Pragmatics in the era of large language models: Ma et al. (2025)
- Jailbreaking with chain of iterative chaos: Yao et al. (2025)
- Tokenization is NP-Complete: Whittington, Bachmann, and Pimentel (2025)
Bibliography
Bezou-Vrakatseli, Elfia, Oana Cocarascu, and Sanjay Modgil. 2025. “Can Large Language Models Understand Argument Schemes?” In Findings of the Association for Computational Linguistics: ACL 2025, edited by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 13666–81. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.findings-acl.702/.
Cheng, Ziling, Meng Cao, Marc-Antoine Rondeau, and Jackie CK Cheung. 2025. “Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs.” In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), edited by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 30187–214. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.acl-long.1458/.
Dong, Honghua, Qidong Su, Yubo Gao, Zhaoyu Li, Yangjun Ruan, Gennady Pekhimenko, Chris J. Maddison, and Xujie Si. 2025. “APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Prompts.” In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), edited by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 1243–66. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.acl-long.63/.
Feger, Marc, Katarina Boland, and Stefan Dietze. n.d. “Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Arguments.”
Gemechu, Debela, Ramon Ruiz-Dolz, Kamila Górska, Somaye Moslemnejad, Eimear Maguire, Dimitra Zografistou, Yohan Jo, John Lawrence, and Chris Reed. 2025. “The Open Argument Mining Framework.” In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), edited by Pushkar Mishra, Smaranda Muresan, and Tao Yu, 318–28. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.acl-demo.31/.
Goffredo, Pierpaolo, Deborah Dore, Elena Cabrio, and Serena Villata. 2025. “DISPUTool 3.0: Fallacy Detection and Repairing in Argumentative Political Debates.” In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), edited by Pushkar Mishra, Smaranda Muresan, and Tao Yu, 472–80. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.acl-demo.45/.
He, Yichen, Guanhua Huang, Peiyuan Feng, Yuan Lin, Yuchen Zhang, Hang Li, and Weinan E. 2025. “PaSa: An LLM Agent for Comprehensive Academic Paper Search.” In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), edited by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 11663–79. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.acl-long.572/.
Jiang, Jin, Yuchen Yan, Yang Liu, Jianing Wang, Shuai Peng, Xunliang Cai, Yixin Cao, Mengdi Zhang, and Liangcai Gao. 2025. “LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning.” In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), edited by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 26200–26218. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.acl-long.1270/.
Khalid, Irtaza, Amir Masoud Nourollah, and Steven Schockaert. 2025. “Large Language and Reasoning Models Are Shallow Disjunctive Reasoners.” In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), edited by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 8843–69. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.acl-long.433/.
Ma, Bolei, Yuting Li, Wei Zhou, Ziwei Gong, Yang Janet Liu, Katja Jasinskaja, Annemarie Friedrich, Julia Hirschberg, Frauke Kreuter, and Barbara Plank. 2025. “Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges.” In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), edited by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 8679–96. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.acl-long.425/.
Mosolova, Anna, Marie Candito, and Carlos Ramisch. 2025. “In the LLM Era, Word Sense Induction Remains Unsolved.” In Findings of the Association for Computational Linguistics: ACL 2025, edited by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 17161–78. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.findings-acl.882/.
Quan, Xin, Marco Valentino, Danilo Carvalho, Dhairya Dalal, and Andre Freitas. 2025. “PEIRCE: Unifying Material and Formal Reasoning via LLM-driven Neuro-Symbolic Refinement.” In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), edited by Pushkar Mishra, Smaranda Muresan, and Tao Yu, 11–21. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.acl-demo.2/.
Quan, Xin, Marco Valentino, Louise A. Dennis, and Andre Freitas. 2025. “Faithful and Robust LLM-driven Theorem Proving for NLI Explanations.” In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), edited by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 17734–55. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.acl-long.867/.
Ranaldi, Leonardo, Marco Valentino, and Andre Freitas. 2025. “Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions.” In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), edited by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 17222–40. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.acl-long.843/.
Raspanti, Federico, Tanir Ozcelebi, and Mike Holenderski. 2025. “Grammar-Constrained Decoding Makes Large Language Models Better Logical Parsers.” In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track), edited by Georg Rehm and Yunyao Li, 485–99. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.acl-industry.34/.
Resnik, Philip. 2025. “Large Language Models Are Biased Because They Are Large Language Models.” March 13, 2025. https://doi.org/10.48550/arXiv.2406.13138.
Ruiz-Dolz, Ramon, Zlata Kikteva, and John Lawrence. 2025. “Mining Complex Patterns of Argumentative Reasoning in Natural Language Dialogue.” In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), edited by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 7421–35. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.acl-long.368/.
Sadeddine, Zacchary, and Fabian M Suchanek. n.d. “Verifying the Steps of Deductive Reasoning Chains.”
Spinoso-Di Piano, Cesare, David Eric Austin, Pablo Piantanida, and Jackie CK Cheung. 2025. “(RSA)²: A Rhetorical-Strategy-Aware Rational Speech Act Framework for Figurative Language Understanding.” In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), edited by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 20898–938. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.acl-long.1019/.
Stahl, Maja, Timon Ziegenbein, Joonsuk Park, and Henning Wachsmuth. 2025. “ArgInstruct: Specialized Instruction Fine-Tuning for Computational Argumentation.” In Findings of the Association for Computational Linguistics: ACL 2025, edited by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 11103–27. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.findings-acl.579/.
Whittington, Philip, Gregor Bachmann, and Tiago Pimentel. 2025. “Tokenisation Is NP-Complete.” In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), edited by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 28133–53. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.acl-long.1365/.
Yao, Yang, Xuan Tong, Ruofan Wang, Yixu Wang, Lujundong Li, Liang Liu, Yan Teng, and Yingchun Wang. 2025. “A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos.” In Findings of the Association for Computational Linguistics: ACL 2025, edited by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 7837–55. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.findings-acl.408/.
Yeginbergen, Anar, Maite Oronoz, and Rodrigo Agerri. 2025. “Dynamic Knowledge Integration for Evidence-Driven Counter-Argument Generation with Large Language Models.” In Findings of the Association for Computational Linguistics: ACL 2025, edited by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 22568–84. Vienna, Austria: Association for Computational Linguistics. https://aclanthology.org/2025.findings-acl.1161/.
Reto Gubelmann 
Leave a comment