English

Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction

Computation and Language 2025-02-12 v1 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.2502.06882,
  title  = {Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction},
  author = {Shengbin Yue and Ting Huang and Zheng Jia and Siyuan Wang and Shujun Liu and Yun Song and Xuanjing Huang and Zhongyu Wei},
  journal= {arXiv preprint arXiv:2502.06882},
  year   = {2025}
}

Comments

Accepted by NAACL 2025

R2 v1 2026-06-28T21:39:11.569Z