跨越全球人工智能监管：一个多司法管辖区的检索增强生成系统
Navigating Global AI Regulation: A Multi-Jurisdictional Retrieval-Augmented Generation System
AI总结：
本文提出一个多司法管辖区的检索增强生成系统，用于全球人工智能监管，通过类型特定分块、条件检索路由和优先级重排序技术，提升法律文档检索效果。
摘要：
跨越不同司法管辖区的人工智能监管日益成为政策制定者、法律专业人士和研究人员的难题。为此，我们提出一个多司法管辖区的检索增强生成系统，用于全球人工智能监管。我们的语料库包含68个司法管辖区的242份文件，涵盖正式立法如欧盟人工智能法案，到无结构政策文件如国家人工智能战略。系统做出了三个技术贡献：类型特定分块，保留法律结构；条件检索路由，利用实体检测和元数据进行法律引用；优先级重排序，提升已实施立法的检索效果。对50个查询的评估显示，在单实体和多司法管辖区问题上表现优异，平均忠实度为0.87，平均回答相关性为0.84。单实体查询平均忠实度为0.86，回答相关性为0.92，而多司法管辖区比较查询平均忠实度为0.88，回答相关性为0.75。这些发现突显了领域特定检索策略在处理复杂、异构监管语料库中的有效性。
英文摘要：
Navigating AI regulation across jurisdictions is increasingly difficult for policymakers, legal professionals, and researchers. To address this, we present a multi-jurisdictional Retrieval-Augmented Generation system for global AI regulation. Our corpus includes 242 documents across 68 jurisdictions, ranging from formal legislation like the EU AI Act to unstructured policy documents such as national AI strategies. The system makes three technical contributions: type-specific chunking that preserve legal structure across heterogenous documents; conditional retrieval routing with entity detection and metadata for legal citations; and priority-based re-ranking to boost enacted legislation over policy and secondary sources. Evaluation of 50 queries reveals strong performance across both single-entity and multi-jurisdictional questions, achieving 0.87 average faithfulness and 0.84 average answer relevancy. Single-entity queries achieve 0.86 average faithfulness and 0.92 average answer relevancy, while multi-jurisdictional comparison queries achieve 0.88 average faithfulness and 0.75 average answer relevancy. These findings highlight the effectiveness of domain-specific retrieval strategies for navigating complex, heterogenous regulatory corpora.
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。
