Chatlaw: A Multi-Agent Collaborative Legal Assistant with Knowledge Graph Enhanced Mixture-of-Experts Large Language Model

Jiaxi Cui, Munan Ning, Zongjian Li, Bohua Chen, Yang Yan +4 more
6/28/2023
cs.CL

No official code found. Best implementation: PKU-YuanGroup/ChatLaw (7,562 stars, AGPL-3.0, last commit 2025-01-04).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

PKU-YuanGroup/ChatLawCommunity100%
AGPL-3.0

ChatLaw：A Powerful LLM Tailored for Chinese Legal. 中文法律大模型

7,562619Jun 7, 20231 years agoAGPL-3.0

Similar Papers

LexAgentHallu: A Hierarchical Benchmark for Profiling Hallucinations in Legal Agents

86% match1 repo2026

A Comprehensive Framework for Reliable Legal AI: Combining Specialized Expert Systems and Adaptive Refinement

83% match2024

LawLuo: A Multi-Agent Collaborative Framework for Multi-Round Chinese Legal Consultation

83% match2024

LegalAgentBench: Evaluating LLM Agents in Legal Domain

82% match1 repo512024

Ready Jurist One: Benchmarking Language Agents for Legal Intelligence in Dynamic Environments

82% match2025

Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergence

82% match2023

Cite this paper

@article{cui2023chatlaw,
  title  = {Chatlaw: A Multi-Agent Collaborative Legal Assistant with Knowledge Graph Enhanced Mixture-of-Experts Large Language Model},
  author = {Jiaxi Cui and Munan Ning and Zongjian Li and Bohua Chen and Yang Yan and Hao Li and Bin Ling and Yonghong Tian and Li Yuan},
  year   = {2023},
  eprint = {2306.16092},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.16092v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.16092.svg)](https://codeofpaper.com/paper/2306.16092)

Discussion