CitaLaw: Enhancing LLM with Citations in Legal Domain

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Kepu, Yu, Weijie, Dai, Sunhao, Xu, Jun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929725595713536
author Zhang, Kepu
Yu, Weijie
Dai, Sunhao
Xu, Jun
author_facet Zhang, Kepu
Yu, Weijie
Dai, Sunhao
Xu, Jun
contents In this paper, we propose CitaLaw, the first benchmark designed to evaluate LLMs' ability to produce legally sound responses with appropriate citations. CitaLaw features a diverse set of legal questions for both laypersons and practitioners, paired with a comprehensive corpus of law articles and precedent cases as a reference pool. This framework enables LLM-based systems to retrieve supporting citations from the reference corpus and align these citations with the corresponding sentences in their responses. Moreover, we introduce syllogism-inspired evaluation methods to assess the legal alignment between retrieved references and LLM-generated responses, as well as their consistency with user questions. Extensive experiments on 2 open-domain and 7 legal-specific LLMs demonstrate that integrating legal references substantially enhances response quality. Furthermore, our proposed syllogism-based evaluation method exhibits strong agreement with human judgments.
format Preprint
id arxiv_https___arxiv_org_abs_2412_14556
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CitaLaw: Enhancing LLM with Citations in Legal Domain
Zhang, Kepu
Yu, Weijie
Dai, Sunhao
Xu, Jun
Computation and Language
In this paper, we propose CitaLaw, the first benchmark designed to evaluate LLMs' ability to produce legally sound responses with appropriate citations. CitaLaw features a diverse set of legal questions for both laypersons and practitioners, paired with a comprehensive corpus of law articles and precedent cases as a reference pool. This framework enables LLM-based systems to retrieve supporting citations from the reference corpus and align these citations with the corresponding sentences in their responses. Moreover, we introduce syllogism-inspired evaluation methods to assess the legal alignment between retrieved references and LLM-generated responses, as well as their consistency with user questions. Extensive experiments on 2 open-domain and 7 legal-specific LLMs demonstrate that integrating legal references substantially enhances response quality. Furthermore, our proposed syllogism-based evaluation method exhibits strong agreement with human judgments.
title CitaLaw: Enhancing LLM with Citations in Legal Domain
topic Computation and Language
url https://arxiv.org/abs/2412.14556