缓解操纵与增强说服：一种用于法律论证生成的反思式多智能体方法
Mitigating Manipulation and Enhancing Persuasion: A Reflective Multi-Agent Approach for Legal Argument Generation
AI总结：
本文提出反思式多智能体方法，通过迭代精炼生成法律论证，有效缓解操纵、增强说服，提升弃权准确性与事实利用。
摘要：
大型语言模型（LLMs）越来越多地被探索用于法律论证生成，然而它们通过幻觉和无根据的说服带来了显著的操纵风险，并且常常无法有效利用所提供的事实基础，或在论证站不住脚时弃权（不执行）。本文提出了一种新颖的反思式多智能体方法，旨在应对这些在法律合规说服背景下的挑战。我们的方法采用专门的智能体（因素分析器和论证润色器）进行迭代精炼过程，以生成三层法律论证（原告、被告、反驳）。我们使用四个不同的LLMs（GPT-4o、GPT-4o-mini、Llama-4-Maverick-17b-128e、Llama-4-Scout-17b-16e）在三种法律场景（“可争辩”、“不匹配”和“不可争辩”）中，将反思式多智能体与单智能体、增强提示单智能体和非反思式多智能体基线进行了评估。结果表明，反思式多智能体方法在成功弃权（不执行）方面表现出色，通过防止在论证无法基于事实时生成内容，提高了幻觉准确性，减少了捏造和错误归因的因素，并通过更好地利用提供的案件事实增强了因素利用召回率。这些发现表明，多智能体框架内的结构化反思为在基于LLM的法律论证系统中促进道德说服和缓解操纵提供了一种稳健的方法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
