Simulating Dispute Mediation with LLM-Based Agents for Legal Research
By: Junjie Chen , Haitao Li , Minghao Qin and more
Potential Business Impact:
Helps lawyers solve arguments using smart computer programs.
Legal dispute mediation plays a crucial role in resolving civil disputes, yet its empirical study is limited by privacy constraints and complex multivariate interactions. To address this limitation, we present AgentMediation, the first LLM-based agent framework for simulating dispute mediation. It simulates realistic mediation processes grounded in real-world disputes and enables controlled experimentation on key variables such as disputant strategies, dispute causes, and mediator expertise. Our empirical analysis reveals patterns consistent with sociological theories, including Group Polarization and Surface-level Consensus. As a comprehensive and extensible platform, AgentMediation paves the way for deeper integration of social science and AI in legal research.
Similar Papers
Chinese Court Simulation with LLM-Based Agent System
Computers and Society
Lets anyone practice being a lawyer in court.
Law in Silico: Simulating Legal Society with LLM-Based Agents
Artificial Intelligence
AI helps test laws and protect people.
Integrating LLM and Diffusion-Based Agents for Social Simulation
Computers and Society
Predicts how ideas spread online better.