用多智能体协作提升大模型对法律理论的理解与推理能力
Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration
- 设计多智能体框架，让模型像人一样拆解复杂法律任务
- 在真实数据集上显著提升法律推理准确率，解决混淆罪名预测难题
- 适合法律AI研究者和司法智能化应用开发者参考
大型语言模型（LLMs）在理解法律理论和执行复杂法律推理任务时存在局限。本文提出一项具有挑战性的任务——混淆罪名预测，以更严格评估模型对法律理论的掌握程度。为此，我们设计了一种新框架MALR（Multi-Agent framework for improving complex Legal Reasoning capability），采用非参数化学习机制，促使LLM自动分解复杂法律任务，并模仿人类学习过程从法律条文中提取深层洞察，从而增强其法律理解与推理能力。在多个真实世界数据集上的大量实验表明，该框架能有效应对实际场景中的复杂推理问题，为法律领域更可靠的AI应用奠定基础。
原文摘要 · Abstract (English)
Large Language Models (LLMs) could struggle to fully understand legal theories and perform complex legal reasoning tasks. In this study, we introduce a challenging task (confusing charge prediction) to better evaluate LLMs' understanding of legal theories and reasoning capabilities. We also propose a novel framework: Multi-Agent framework for improving complex Legal Reasoning capability (MALR). MALR employs non-parametric learning, encouraging LLMs to automatically decompose complex legal tasks and mimic human learning process to extract insights from legal rules, helping LLMs better understand legal theories and enhance their legal reasoning abilities. Extensive experiments on multiple real-world datasets demonstrate that the proposed framework effectively addresses complex reasoning issues in practical scenarios, paving the way for more reliable applications in the legal domain.
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。