Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering
Yinghao Hu, Leilei Gan, Wenyi Xiao, Kun Kuang, Fei Wu
Abstract
Hallucination, or the generation of incorrect or fabricated information, remains a critical challenge in large language models (LLMs), particularly in high-stake domains such as legal question answering (QA). In order to mitigate the hallucination rate in legal QA, we first introduce a benchmark called LegalHalBench and three automatic metrics to evaluate the common hallucinations when LLMs answer legal questions. We then propose a hallucination mitigation method that integrates behavior cloning and a novel Hard Sample-aware Iterative Direct Preference Optimization (HIPO). We conduct extensive real-data experiments to validate the effectiveness of our approach. Our results demonstrate remarkable improvements in various metrics, including the newly proposed Non-Hallucinated Statute Rate, Statute Relevance Rate, Legal Claim Truthfulness, as well as traditional metrics such as METEOR, BERTScore, ROUGE-L, and win rates.
BibTeX
@inproceedings{hu-etal-2025-fine,
title = "Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering",
author = "Hu, Yinghao and
Gan, Leilei and
Xiao, Wenyi and
Kuang, Kun and
Wu, Fei",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.298/",
pages = "4410--4427"
}