Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction
Shengbin Yue, Ting Huang, Zheng Jia, Siyuan Wang, Shujun Liu, Yun Song, Xuanjing Huang, Zhongyu Wei
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.
BibTeX
@inproceedings{shengbinyue-etal-2025-multi,
title = "Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction",
author = "Yue, Shengbin and
Huang, Ting and
Jia, Zheng and
Wang, Siyuan and
Liu, Shujun and
Song, Yun and
Huang, Xuanjing and
Wei, Zhongyu",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.365/",
pages = "6537--6570",
ISBN = "979-8-89176-195-7"
}