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.

翻译：基于大语言模型（LLM）的人工智能法律助手能够提供便捷的法律咨询服务，但其存在的幻觉问题会带来潜在的法律风险。本文提出Chatlaw，一种创新的法律助手，它利用混合专家（MoE）模型和多智能体系统来提升人工智能驱动的法律服务的可靠性与准确性。通过将知识图谱与人工筛选相结合，我们构建了一个高质量的法律数据集来训练MoE模型。该模型利用不同的专家处理各类法律问题，从而优化法律答复的准确性。此外，借鉴真实律师事务所工作流程设计的标准化操作程序（SOP），显著减少了法律服务中的错误与幻觉。我们的MoE模型在法律基准测试和法律职业资格统一考试中的准确率分别超过GPT-4达7.73%和11分，并且在真实案例咨询的多个维度上也优于其他模型，展现了我们强大的法律咨询能力。