Abstract
Text-generative models have proven to be good reasoners. Although reasoning abilities are mostly observed in larger language models, a number of strategies try to transfer this skill to smaller language models. This paper presents our approach to SemEval 2024 Task-5: The Legal Argument Reasoning Task in Civil Procedure. This shared task aims to develop a system that efficiently handles a multiple-choice question-answering task in the context of the US civil procedure domain. The dataset provides a human-generated rationale for each answer. Given the complexity of legal issues, this task certainly challenges the reasoning abilities of LLMs and AI systems in general. Our work explores fine-tuning an LLM as a correct/incorrect answer classifier. In this context, we are making use of multi-task learning toincorporate the rationales into the fine-tuning process.- Anthology ID:
- 2024.semeval-1.152
- Volume:
- Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
- Month:
- June
- Year:
- 2024
- Address:
- Mexico City, Mexico
- Editors:
- Atul Kr. Ojha, A. Seza Doğruöz, Harish Tayyar Madabushi, Giovanni Da San Martino, Sara Rosenthal, Aiala Rosá
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1053–1057
- Language:
- URL:
- https://aclanthology.org/2024.semeval-1.152
- DOI:
- Cite (ACL):
- Ioannis Maslaris and Avi Arampatzis. 2024. DUTh at SemEval 2024 Task 5: A multi-task learning approach for the Legal Argument Reasoning Task in Civil Procedure. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 1053–1057, Mexico City, Mexico. Association for Computational Linguistics.
- Cite (Informal):
- DUTh at SemEval 2024 Task 5: A multi-task learning approach for the Legal Argument Reasoning Task in Civil Procedure (Maslaris & Arampatzis, SemEval 2024)
- PDF:
- https://preview.aclanthology.org/jeptaln-2024-ingestion/2024.semeval-1.152.pdf