Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cui, Jiaxi, Ning, Munan, Li, Zongjian, Chen, Bohua, Yan, Yang, Li, Hao, Ling, Bin, Tian, Yonghong, Yuan, Li
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2306.16092
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913369611567104
author Cui, Jiaxi
Ning, Munan
Li, Zongjian
Chen, Bohua
Yan, Yang
Li, Hao
Ling, Bin
Tian, Yonghong
Yuan, Li
author_facet Cui, Jiaxi
Ning, Munan
Li, Zongjian
Chen, Bohua
Yan, Yang
Li, Hao
Ling, Bin
Tian, Yonghong
Yuan, Li
contents AI legal assistants based on Large Language Models (LLMs) can provide accessible legal consulting services, but the hallucination problem poses potential legal risks. This paper presents Chatlaw, an innovative legal assistant utilizing a Mixture-of-Experts (MoE) model and a multi-agent system to enhance the reliability and accuracy of AI-driven legal services. By integrating knowledge graphs with artificial screening, we construct a high-quality legal dataset to train the MoE model. This model utilizes different experts to address various legal issues, optimizing the accuracy of legal responses. Additionally, Standardized Operating Procedures (SOP), modeled after real law firm workflows, significantly reduce errors and hallucinations in legal services. Our MoE model outperforms GPT-4 in the Lawbench and Unified Qualification Exam for Legal Professionals by 7.73% in accuracy and 11 points, respectively, and also surpasses other models in multiple dimensions during real-case consultations, demonstrating our robust capability for legal consultation.
format Preprint
id arxiv_https___arxiv_org_abs_2306_16092
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Chatlaw: A Multi-Agent Collaborative Legal Assistant with Knowledge Graph Enhanced Mixture-of-Experts Large Language Model
Cui, Jiaxi
Ning, Munan
Li, Zongjian
Chen, Bohua
Yan, Yang
Li, Hao
Ling, Bin
Tian, Yonghong
Yuan, Li
Computation and Language
AI legal assistants based on Large Language Models (LLMs) can provide accessible legal consulting services, but the hallucination problem poses potential legal risks. This paper presents Chatlaw, an innovative legal assistant utilizing a Mixture-of-Experts (MoE) model and a multi-agent system to enhance the reliability and accuracy of AI-driven legal services. By integrating knowledge graphs with artificial screening, we construct a high-quality legal dataset to train the MoE model. This model utilizes different experts to address various legal issues, optimizing the accuracy of legal responses. Additionally, Standardized Operating Procedures (SOP), modeled after real law firm workflows, significantly reduce errors and hallucinations in legal services. Our MoE model outperforms GPT-4 in the Lawbench and Unified Qualification Exam for Legal Professionals by 7.73% in accuracy and 11 points, respectively, and also surpasses other models in multiple dimensions during real-case consultations, demonstrating our robust capability for legal consultation.
title Chatlaw: A Multi-Agent Collaborative Legal Assistant with Knowledge Graph Enhanced Mixture-of-Experts Large Language Model
topic Computation and Language
url https://arxiv.org/abs/2306.16092