RAGulating Compliance: A Multi-Agent Knowledge Graph for Regulatory QA

TL;DR

This paper introduces a multi-agent system combining a regulatory knowledge graph with retrieval-augmented generation to improve accuracy, traceability, and understanding in regulatory compliance question answering.

Contribution

It presents a novel framework integrating a dynamic, ontology-free knowledge graph with RAG for regulatory QA, enhancing factual correctness and traceability.

Findings

Outperforms conventional methods on complex regulatory queries

Ensures factual correctness through embedded triplets

Provides traceability and visualization via a unified vector database

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.