MAINDZ at SemEval-2024 Task 5: CLUEDO - Choosing Legal oUtcome by Explaining Decision through Oversight

Irene Benedetto, Alkis Koudounas, Lorenzo Vaiani, Eliana Pastor, Luca Cagliero, Francesco Tarasconi


Abstract
Large language models (LLMs) have recently obtained strong performance on complex reasoning tasks. However, their capabilities in specialized domains like law remain relatively unexplored. We present CLUEDO, a system to tackle a novel legal reasoning task that involves determining if a provided answer correctly addresses a legal question derived from U.S. civil procedure cases. CLUEDO utilizes multiple collaborator models that are trained using multiple-choice prompting to choose the right label and generate explanations. These collaborators are overseen by a final “detective” model that identifies the most accurate answer in a zero-shot manner. Our approach achieves an F1 macro score of 0.74 on the development set and 0.76 on the test set, outperforming individual models. Unlike the powerful GPT-4, CLUEDO provides more stable predictions thanks to the ensemble approach. Our results showcase the promise of tailored frameworks to enhance legal reasoning capabilities in LLMs.
Anthology ID:
2024.semeval-1.144
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:
997–1005
Language:
URL:
https://aclanthology.org/2024.semeval-1.144
DOI:
10.18653/v1/2024.semeval-1.144
Bibkey:
Cite (ACL):
Irene Benedetto, Alkis Koudounas, Lorenzo Vaiani, Eliana Pastor, Luca Cagliero, and Francesco Tarasconi. 2024. MAINDZ at SemEval-2024 Task 5: CLUEDO - Choosing Legal oUtcome by Explaining Decision through Oversight. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 997–1005, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
MAINDZ at SemEval-2024 Task 5: CLUEDO - Choosing Legal oUtcome by Explaining Decision through Oversight (Benedetto et al., SemEval 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.semeval-1.144.pdf
Supplementary material:
 2024.semeval-1.144.SupplementaryMaterial.zip
Supplementary material:
 2024.semeval-1.144.SupplementaryMaterial.tex
Supplementary material:
 2024.semeval-1.144.SupplementaryMaterial.txt