用多智能体反思机制提升法律论点生成的可信度与合规性。
Mitigating Manipulation and Enhancing Persuasion: A Reflective Multi-Agent Approach for Legal Argument Generation
- 设计反思型多智能体架构，分步生成原告、被告及反驳论点。
- 在不可辩案件中有效放弃生成，减少幻觉并提升事实使用率。
- 适合法律AI伦理、司法辅助系统研发者参考。
大型语言模型（LLMs）被广泛探索用于法律论点生成，但存在幻觉和无根据说服的风险，且难以有效利用给定事实或在论点不可行时主动停止生成。本文提出一种新型反思式多智能体方法，通过因子分析员与论点润色员的迭代优化，生成三段式法律论点（原告、被告、反驳）。我们在三个法律场景（可辩、事实不匹配、不可辩）下，使用四种LLM（GPT-4o、GPT-4o-mini、Llama-4-Maverick-17b-128e、Llama-4-Scout-17b-16e）进行评估。结果表明，该方法能有效实现不可行时的主动放弃生成，降低虚构与误归因因子比例，并显著提升对已提供事实的利用率。研究显示，在多智能体框架中引入结构化反思，是实现合规说服与防范操纵的有效路径。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are increasingly explored for legal argument generation, yet they pose significant risks of manipulation through hallucination and ungrounded persuasion, and often fail to utilize provided factual bases effectively or abstain when arguments are untenable. This paper introduces a novel reflective multi-agent method designed to address these challenges in the context of legally compliant persuasion. Our approach employs specialized agents (factor analyst and argument polisher) in an iterative refinement process to generate 3-ply legal arguments (plaintiff, defendant, rebuttal). We evaluate reflective multi-agent against single-agent, enhanced-prompt single-agent, and non-reflective multi-agent baselines using four diverse LLMs (GPT-4o, GPT-4o-mini, Llama-4-Maverick-17b-128e, Llama-4-Scout-17b-16e) across three legal scenarios: "arguable", "mismatched", and "non-arguable". Results demonstrate that the reflective multi-agent approach excels at successful abstention by preventing generation when arguments cannot be grounded, improves hallucination accuracy by reducing fabricated and misattributed factors and enhances factor utilization recall by better using the provided case facts. These findings suggest that structured reflection within a multi-agent framework offers a robust method for fostering ethical persuasion and mitigating manipulation in LLM-based legal argumentation systems.
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。