Maat: 面向竞争保护的法律研究智能助手
Maat: The Agentic Legal Research Assistant for Competition Protection
AI总结:
提出Maat,一种基于ReAct框架的智能法律研究助手,通过RAG、网络搜索和用户澄清机制,在竞争法案例检索中显著优于现有通用和专用法律助手。
摘要:
进行法律研究的竞争法专家必须查阅大量案例、决定和司法报告,以识别先例并评估竞争和合并案件中的关键要素。尽管通用研究助手(如Claude和ChatGPT)和法律助手(如SaulLM-7B和LegalGPT)越来越多地被用于辅助法律研究,但它们在竞争法分析方面仍然不足:缺乏专门的领域知识,提供不充分的官方引用,或虚构竞争法案例。我们提出Maat,一个ReAct智能体,它协调与研究过程不同任务对应的工具。Maat与竞争法专家迭代设计,使用RAG将案例和发现基于官方来源以确保可靠性,提供丰富的行内引用,在数据库覆盖不足时回退到网络搜索,并在查询模糊时提示用户澄清。Maat在案例特定任务上显著优于所有基线助手,在理论问题任务上表现与最佳基线相当。所使用的数据集可在GitHub上获取。
英文摘要:
Competition law experts conducting legal research must review extensive volumes of cases, decisions, and judicial reports to identify precedents and assess key elements in competition and merger cases. Although general research assistants such as Claude and ChatGPT and legal assistants such as SaulLM-7B and LegalGPT are increasingly used to assist legal research, they remain inadequate for competition law analysis: they lack specialized domain expertise, provide insufficient official citations, or hallucinate competition law cases. We propose Maat, a ReAct agent that orchestrates tools corresponding to different tasks of the research process. Designed iteratively with competition law experts, Maat grounds cases and findings in official sources using RAG for reliability, provides rich in-line citations, falls back to web search when database coverage is insufficient, and prompts the user for clarification when queries are ambiguous. Maat significantly outperforms all baseline assistants on case-specific tasks and performs within range of the top baseline on theoretical question tasks. The dataset used is available on GitHub.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。