让大模型回答合规问题时能精准追踪每条法规来源。
Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering
- 用共享主题锚点遍历跨文档引用，统一检索路径。
- 在测试中召回率与引用准确率显著提升，优于现有系统。
- 适合需要严格溯源的金融、医疗等合规领域应用。
将大语言模型用于监管合规问答需确保跨多层级权威体系的完整引用追溯。与传统多跳或法律问答不同，该任务要求结构化流程查找与证据集闭合，而非实体消解或判例推理。现有RAG系统在此面临引用边扁平化、检索扩展碎片化及事后归因脆弱等问题。我们提出RegOps-Bench基准，基于复杂国家研发监管法规构建操作知识图谱。针对瓶颈，提出RefWalk框架：以共享主题锚点驱动跨文档引用遍历，通过最大值聚合融合多视角候选，并强制逐规则归因，显式映射主张与来源。实验建立强基线，检索召回率和引用准确率均有显著提升。在美国健康合规数据集（HIPAA）上的对比评估显示，现有系统在扁平结构规则上已出现性能饱和，凸显RegOps-Bench的必要性。代码开源于https://github.com/yeongjoonJu/RefWalk。
原文摘要 · Abstract (English)
Deploying Large Language Models (LLMs) for regulatory compliance demands rigorous traceability via comprehensive citations across multi-tiered authority structures. Unlike traditional multi-hop or legal QA, this task requires structured procedural lookups and evidence-set closure rather than entity resolution or case-law reasoning. Existing RAG systems struggle here due to flattened citation edges, fragmented retrieval expansions, and fragile post-hoc attribution. We formalize Regulatory Compliance QA with RegOps-Bench, a novel benchmark featuring an Operational Knowledge Graph derived from complex national R\&D regulations. To address these bottlenecks, we propose RefWalk, a unified framework driven by a shared topic anchor. RefWalk traverses cross-document citations, fuses multi-view candidates via max-based aggregation, and enforces per-rule attribution to explicitly map claims to sources. We establish a strong baseline with substantial improvements in retrieval recall and citation accuracy. Finally, a contrastive evaluation on a U.S. health compliance dataset (HIPAA) reveals that existing systems exhibit saturation on flat-structure rules, underscoring the need for RegOps-Bench. Our code is available at https://github.com/yeongjoonJu/RefWalk.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。