NLP at UC Santa Cruz at SemEval-2024 Task 5: Legal Answer Validation using Few-Shot Multi-Choice QA

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pahilajani, Anish, Jain, Samyak Rajesh, Trivedi, Devasha
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913298583126016
author Pahilajani, Anish
Jain, Samyak Rajesh
Trivedi, Devasha
author_facet Pahilajani, Anish
Jain, Samyak Rajesh
Trivedi, Devasha
contents This paper presents our submission to the SemEval 2024 Task 5: The Legal Argument Reasoning Task in Civil Procedure. We present two approaches to solving the task of legal answer validation, given an introduction to the case, a question and an answer candidate. Firstly, we fine-tuned pre-trained BERT-based models and found that models trained on domain knowledge perform better. Secondly, we performed few-shot prompting on GPT models and found that reformulating the answer validation task to be a multiple-choice QA task remarkably improves the performance of the model. Our best submission is a BERT-based model that achieved the 7th place out of 20.
format Preprint
id arxiv_https___arxiv_org_abs_2404_03150
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle NLP at UC Santa Cruz at SemEval-2024 Task 5: Legal Answer Validation using Few-Shot Multi-Choice QA
Pahilajani, Anish
Jain, Samyak Rajesh
Trivedi, Devasha
Computation and Language
Artificial Intelligence
This paper presents our submission to the SemEval 2024 Task 5: The Legal Argument Reasoning Task in Civil Procedure. We present two approaches to solving the task of legal answer validation, given an introduction to the case, a question and an answer candidate. Firstly, we fine-tuned pre-trained BERT-based models and found that models trained on domain knowledge perform better. Secondly, we performed few-shot prompting on GPT models and found that reformulating the answer validation task to be a multiple-choice QA task remarkably improves the performance of the model. Our best submission is a BERT-based model that achieved the 7th place out of 20.
title NLP at UC Santa Cruz at SemEval-2024 Task 5: Legal Answer Validation using Few-Shot Multi-Choice QA
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2404.03150