用大模型模拟中国民事法庭审判，实现可扩展的法律实践训练。
Civil Court Simulation with Large Language Models
- 构建五阶段民事庭审流程的多智能体框架，支持角色互动与记忆检索。
- 在责任分配和多事项判决上表现可靠，记忆质量显著影响模拟效果。
- 适合法律教育、司法研究者，尤其关注民事案件模拟的应用场景。
法庭模拟连接法律教育与司法实践，但人工模拟成本高且难以扩展。大语言模型（LLMs）提供了可扩展的替代方案，但现有研究多集中于刑事案例。民事诉讼在实践中更常见，且因诉求、责任和救济方式更具灵活性而更难模拟。本文提出一个面向中国民事案件的多智能体法庭模拟框架，通过五阶段民事审判程序组织角色间互动，并集成记忆模块与法规检索机制以支持长流程裁判。实验表明，该框架生成的判决结果可靠，在责任分配和多事项判决方面表现突出。进一步实验显示，记忆质量对下游模拟效果有显著影响。基于五层因素框架，分析了法律依据、信息条件、司法能力与角色定位、组织压力及社会背景对框架可靠性与行为的影响。这些结果验证了所提框架在民事法庭模拟中的有效性。数据集与代码已公开：https://github.com/foggpoy/Civil-Court。
原文摘要 · Abstract (English)
Court simulation bridges legal education and judicial practice, yet human-based simulations are costly and difficult to scale. Large language models (LLMs) offer a scalable alternative, but existing court-simulation research mainly focuses on criminal cases. Civil litigation is more common in practice and harder to simulate because its claims, liability, and remedies are more flexible. We present a multi-agent court simulation framework for Chinese civil cases. The framework organizes role-based interaction through a five-stage civil trial procedure and integrates memory module and statute retrieval to support long-process adjudication. Experiments show that the framework produces reliable civil judgments, with clear strengths in liability allocation and multi-item adjudication. Further experiments show that memory quality substantially affects downstream simulation quality. Through a five-layer factor framework, we analyze how legal grounding, information conditions, judicial capability and role orientation, organizational pressure, and social context affect the framework's reliability and behavior. These results support the effectiveness of the proposed framework for civil court simulation. The dataset and code are available at: https://github.com/foggpoy/Civil-Court.
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。