Abstract
Regulatory compliance question answering (QA) requires precise, verifiable information, and domain-specific expertise, posing challenges for Large Language Models (LLMs). In this work, we present a novel multi-agent framework that integrates a Knowledge Graph (KG) of Regulatory triplets with Retrieval-Augmented Generation (RAG) to address these demands. First, agents build and maintain an ontology-free KG by extracting subject--predicate--object (SPO) triplets from regulatory documents and systematically cleaning, normalizing, deduplicating, and updating them. Second, these triplets are embedded and stored along with their corresponding textual sections and metadata in a single enriched vector database, allowing for both graph-based reasoning and efficient information retrieval. Third, an orchestrated agent pipeline leverages triplet-level retrieval for question answering, ensuring high semantic alignment between user queries and the factual "who-did-what-to-whom" core captured by the graph. Our hybrid system outperforms conventional methods in complex regulatory queries, ensuring factual correctness with embedded triplets, enabling traceability through a unified vector database, and enhancing understanding through subgraph visualization, providing a robust foundation for compliance-driven and broader audit-focused applications.
Abstract (translated)
监管合规问答（QA）需要精确、可验证的信息以及特定领域的专业知识，这对大型语言模型（LLM）提出了挑战。在这项工作中，我们提出了一种新颖的多代理框架，该框架将知识图谱（KG）与增强检索生成技术（RAG）相结合，以满足这些需求。首先，代理通过从监管文件中提取主语-谓词-宾语（SPO）三元组，并对其进行系统地清理、规范化、去重和更新来构建并维护无本体论的知识图谱。其次，这些三元组连同其对应的文本部分和元数据一起嵌入并存储在一个单一的丰富向量数据库中，这使得基于图形推理和高效信息检索成为可能。第三，一个编排的代理管道利用三元组级别的检索来回答问题，确保用户查询与图谱所捕获的事实“谁做了什么给谁”核心之间具有高度语义一致性。我们的混合系统在处理复杂的监管查询时超越了传统方法，在保证事实准确性、通过统一向量数据库实现可追溯性以及通过子图可视化增强理解方面提供了坚实的基础，从而为合规驱动和更广泛的审计聚焦应用提供支持。
URL
https://arxiv.org/abs/2508.09893
