用多智能体模拟生成法律交互数据，提升大模型实战能力
Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction
- 构建多智能体仿真系统，自动生成真实法律场景数据
- 通过监督机制保证角色行为一致，减少干扰因素
- 设计动态评估基准，专门测试模型在复杂法律交互中的表现
大语言模型在法律智能领域已取得显著进展，但交互式法律场景数据稀缺制约了进一步发展。本文提出多智能体法律仿真驱动框架（MASER），通过模拟真实法律案例，可规模化生成合成数据。该框架基于真实案件源，确保参与者间法律属性的一致性，并引入监督机制，对参与者角色与行为进行对齐，有效缓解干扰问题。此外，构建了多阶段交互式法律评估基准（MILE），用于评估大模型在动态法律场景中的表现。大量实验验证了该框架的有效性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have significantly advanced legal intelligence, but the scarcity of scenario data impedes the progress toward interactive legal scenarios. This paper introduces a Multi-agent Legal Simulation Driver (MASER) to scalably generate synthetic data by simulating interactive legal scenarios. Leveraging real-legal case sources, MASER ensures the consistency of legal attributes between participants and introduces a supervisory mechanism to align participants' characters and behaviors as well as addressing distractions. A Multi-stage Interactive Legal Evaluation (MILE) benchmark is further constructed to evaluate LLMs' performance in dynamic legal scenarios. Extensive experiments confirm the effectiveness of our framework.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。