Navigating Global AI Regulation: A Multi-Jurisdictional Retrieval-Augmented Generation System

• URL: http://arxiv.org/abs/2604.25448v1
• Date: Tue, 28 Apr 2026 09:58:18 GMT
• Title: Navigating Global AI Regulation: A Multi-Jurisdictional Retrieval-Augmented Generation System
• Abstract summary: We present a multi-jurisdictional Retrieval-Augmented Generation system for global AI regulation.<n>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.
• Score: 1.4700417433722486
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• CoAL-RAG: A Complexity-Aware Legal Retrieval-Augmented Generation Method [6.751636537163415]
  CoAL-RAG is a complexity-aware legal retrieval-augmented generation method.<n>It constructs a multi-dimensional evaluation mechanism based on question essence'' and retrieval consistency''<n>On Chinese datasets, the BLEU score improves by 42.5% and ROUGE-L reaches 3.6 times that of knowledge graph-based methods.
  arXiv  Detail & Related papers  (2026-08-18T08:58:11Z)
• Achieving Text-based Person Retrieval with Any Granularity [80.69427598925718]
  This paper introduces a new paradigm, Text-based Person Retrieval with Any Granularity.<n>We formalize a five-level granularity spectrum and construct UFine6926-MG, a high-quality multi-grained annotated dataset.<n>We then propose the Cross-modal Multi-grained Aligning and Matching framework.
  arXiv  Detail & Related papers  (2026-07-23T08:42:25Z)
• From Norms to Indicators (N2I-RAG): An Agentic Retrieval-Augmented Generation Framework for Legal Indicator Computation [0.0]
  This paper presents N2I-RAG, an agentic retrieval-augmented generation framework designed to automate the computation of legal indicators.<n>We integrate adaptive retrieval, llm-based agents, and validation mechanisms in a modular pipeline, where each component performs a defined role in filtering, retrieving, and assessing evidence.<n>We evaluate N2I-RAG using an in-house constructed French marine environmental law corpus that includes both scanned and digital sources.
  arXiv  Detail & Related papers  (2026-05-26T12:21:48Z)
• Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA [5.182285573627426]
  We study the application of RAG to AI governance and policy analysis using the AI Governance and Regulatory Archive corpus.<n>Our system combines a ColBERT-based retriever fine-tuned with contrastive learning and a generator aligned to human preferences.<n>We find that domain-specific fine-tuning improves retrieval metrics but does not consistently improve end-to-end question answering performance.
  arXiv  Detail & Related papers  (2026-03-25T17:54:39Z)
• Security, privacy, and agentic AI in a regulatory view: From definitions and distinctions to provisions and reflections [53.468443050795344]
  The rapid proliferation of artificial intelligence (AI) technologies has led to a dynamic regulatory landscape.<n>As AI paradigms shift towards greater autonomy, specifically in the form of agentic AI, it becomes increasingly challenging to articulate regulatory stipulations.<n>This paper reviews the evolving European Union (EU) AI regulatory provisions via analyzing 24 relevant documents published between 2024 and 2025.
  arXiv  Detail & Related papers  (2026-03-19T13:50:52Z)
• Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage [89.58253972744531]
  Retrieval-augmented generation (RAG) systems combine document retrieval with a generative model to address complex information seeking tasks like report generation.<n>We investigate whether upstream retrieval metrics can serve as reliable early indicators of the final generated response's information coverage.<n>Our findings demonstrate strong correlations between coverage-based retrieval metrics and nugget coverage in generated responses at both topic and system levels.
  arXiv  Detail & Related papers  (2026-03-09T18:20:20Z)
• LegalOne: A Family of Foundation Models for Reliable Legal Reasoning [54.57434222018289]
  We present LegalOne, a family of foundational models specifically tailored for the Chinese legal domain.<n>LegalOne is developed through a comprehensive three-phase pipeline designed to master legal reasoning.<n>We publicly release the LegalOne weights and the LegalKit evaluation framework to advance the field of Legal AI.
  arXiv  Detail & Related papers  (2026-01-31T10:18:32Z)
• Judicial Requirements for Generative AI in Legal Reasoning [0.0]
  Large Language Models (LLMs) are being integrated into professional domains, yet their limitations in high-stakes fields like law remain poorly understood.<n>This paper defines the core capabilities that an AI system must possess to function as a reliable reasoning tool in judicial decision-making.
  arXiv  Detail & Related papers  (2025-08-26T09:56:26Z)
• ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation [56.79698529022327]
  Legal claims refer to the plaintiff's demands in a case and are essential to guiding judicial reasoning and case resolution.<n>This paper explores the problem of legal claim generation based on the given case's facts.<n>We construct ClaimGen-CN, the first dataset for Chinese legal claim generation task.
  arXiv  Detail & Related papers  (2025-08-24T07:19:25Z)
• Augmented Question-guided Retrieval (AQgR) of Indian Case Law with LLM, RAG, and Structured Summaries [0.0]
  This paper proposes the use of Large Language Models (LLMs) to facilitate the retrieval of relevant cases.<n>Our approach combines Retrieval Augmented Generation (RAG) with structured summaries optimized for Indian case law.<n>The system generates targeted legal questions based on factual scenarios to identify relevant case law more effectively.
  arXiv  Detail & Related papers  (2025-07-23T05:24:44Z)
• Bridging Legal Knowledge and AI: Retrieval-Augmented Generation with Vector Stores, Knowledge Graphs, and Hierarchical Non-negative Matrix Factorization [6.0045906216050815]
  Agentic Generative AI, powered by Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG), Knowledge Graphs (KGs), and Vector Stores (VSs)<n>This technology excels at inferring relationships within vast unstructured or semi-structured datasets.<n>We introduce a generative AI system that integrates RAG, VS, and KG, constructed via Non-Negative Matrix Factorization (NMF)
  arXiv  Detail & Related papers  (2025-02-27T18:35:39Z)
• JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking [81.88787401178378]
  We introduce JudgeRank, a novel agentic reranker that emulates human cognitive processes when assessing document relevance. We evaluate JudgeRank on the reasoning-intensive BRIGHT benchmark, demonstrating substantial performance improvements over first-stage retrieval methods. In addition, JudgeRank performs on par with fine-tuned state-of-the-art rerankers on the popular BEIR benchmark, validating its zero-shot generalization capability.
  arXiv  Detail & Related papers  (2024-10-31T18:43:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.