arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.03418cs.AIcs.MA
收藏

LegalWiz：一种用于法律文档矛盾检测的多智能体生成框架

LegalWiz: A Multi-Agent Generation Framework for Contradiction Detection in Legal Documents

Centific；Amazon（亚马逊）

Ananya Mantravadi, Shivali Dalmia, Olga Pospelova, Abhishek Mukherji, Nand Dave, Anudha Mittal

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出LegalWiz多智能体框架，通过生成合成法律文档并注入六种结构化矛盾类型，为法律RAG管道提供首个矛盾感知评估基准，支持更可信的系统。

摘要：

检索增强生成（RAG）将大型语言模型（LLM）与外部来源结合，但检索证据中未解决的矛盾常导致幻觉和不符合法律的输出。当前用于矛盾检测的基准缺乏领域真实感，仅覆盖有限的冲突类型，且很少扩展到单句对之外，使其不适用于法律应用。因此，生成嵌入了矛盾的可控文档至关重要：它能够对模型进行系统压力测试，确保覆盖多样化的冲突类别，并为评估矛盾检测和解决提供可靠基础。我们提出了一个面向法律领域的多智能体矛盾感知基准框架，该框架生成合成法律风格文档，注入六种结构化矛盾类型，并对自身和成对不一致性进行建模。自动化矛盾挖掘与人在回路验证相结合，以确保合理性和保真度。该基准为法律RAG管道中的矛盾感知评估提供了首批结构化资源之一，支持更一致、可解释和可信的系统。

英文摘要：

Retrieval-Augmented Generation (RAG) integrates large language models (LLMs) with external sources, but unresolved contradictions in retrieved evidence often lead to hallucinations and legally unsound outputs. Benchmarks currently used for contradiction detection lack domain realism, cover only limited conflict types, and rarely extend beyond single-sentence pairs, making them unsuitable for legal applications. Controlled generation of documents with embedded contradictions is therefore essential: it enables systematic stress-testing of models, ensures coverage of diverse conflict categories, and provides a reliable basis for evaluating contradiction detection and resolution. We present a multi-agent contradiction-aware benchmark framework for the legal domain that generates synthetic legal-style documents, injects six structured contradiction types, and models both self- and pairwise inconsistencies. Automated contradiction mining is combined with human-in-the-loop validation to guarantee plausibility and fidelity. This benchmark offers one of the first structured resources for contradiction-aware evaluation in legal RAG pipelines, supporting more consistent, interpretable, and trustworthy 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。

↑