AUTOLAW：通过判例生成与陪审团式审议增强大型语言模型的法律合规性
AUTOLAW: Enhancing Legal Compliance in Large Language Models via Case Law Generation and Jury-Inspired Deliberation
AI总结：
AutoLaw通过对抗性数据生成与陪审团式审议，动态合成判例并模拟司法决策，在三个基准上显著提升LLM的法律违规检测率，实现可靠且情境感知的合规评估。
摘要：
法律等领域中领域特定大型语言模型（LLM）的快速发展，要求框架能够考虑细微的区域法律差异，这对于确保合规性和可信度至关重要。现有的法律评估基准往往缺乏适应性，无法应对多样化的地方背景，限制了其在动态演变的监管环境中的实用性。为解决这些不足，我们提出了AutoLaw，一种新颖的违规检测框架，它将对抗性数据生成与陪审团式审议过程相结合，以增强LLM的法律合规性。与静态方法不同，AutoLaw动态合成判例以反映当地法规，并利用一组基于LLM的“陪审员”来模拟司法决策。陪审员根据综合的法律专业知识进行排名和选择，从而实现减少偏见并提高检测准确性的审议过程。在三个基准上的评估：Law-SG、Case-SG（合法性）和Unfair-TOS（政策），证明了AutoLaw的有效性：对抗性数据生成提高了LLM的判别能力，而基于陪审团的投票策略显著提升了违规检测率。我们的结果凸显了该框架自适应探测法律错位并提供可靠、情境感知判断的能力，为在法律敏感应用中评估和增强LLM提供了一种可扩展的解决方案。
英文摘要：
The rapid advancement of domain-specific large language models (LLMs) in fields like law necessitates frameworks that account for nuanced regional legal distinctions, which are critical for ensuring compliance and trustworthiness. Existing legal evaluation benchmarks often lack adaptability and fail to address diverse local contexts, limiting their utility in dynamically evolving regulatory landscapes. To address these gaps, we propose AutoLaw, a novel violation detection framework that combines adversarial data generation with a jury-inspired deliberation process to enhance legal compliance of LLMs. Unlike static approaches, AutoLaw dynamically synthesizes case law to reflect local regulations and employs a pool of LLM-based "jurors" to simulate judicial decision-making. Jurors are ranked and selected based on synthesized legal expertise, enabling a deliberation process that minimizes bias and improves detection accuracy. Evaluations across three benchmarks: Law-SG, Case-SG (legality), and Unfair-TOS (policy), demonstrate AutoLaw's effectiveness: adversarial data generation improves LLM discrimination, while the jury-based voting strategy significantly boosts violation detection rates. Our results highlight the framework's ability to adaptively probe legal misalignments and deliver reliable, context-aware judgments, offering a scalable solution for evaluating and enhancing LLMs in legally sensitive applications.
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。
