LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning
Zerui Chen, Qinggang Zhang, Zhishang Xiang, Zhimin Wei, Linfeng Gao, Xiao Huang, Zhihong Zhang, Jinsong Su
Why It Matters
What makes this one worth your time
This framework addresses critical challenges in legal AI by ensuring transparency and reliability in legal judgments, which is essential for practitioners and researchers in the field.
LegalGraphRAG improves legal reasoning through structured retrieval and verification.
Summary
The paper presents LegalGraphRAG, a framework that enhances legal reasoning by utilizing a hierarchical legal graph and a multi-agent system to ensure reliable retrieval and verification of legal evidence.
Key contributions
- Development of a hierarchical legal graph for structured knowledge representation.
- Implementation of a multi-agent system for evidence retrieval and verification in legal reasoning.
Notable insights
- The introduction of a hierarchical legal graph allows for nuanced retrieval of legal information at different abstraction levels.
- The multi-agent system enhances the reliability of legal reasoning by incorporating roles for evidence retrieval, verification, and synthesis.
Possible limitations
- Not stated in the abstract.
Abstract
arXiv:2605.28120v1 Announce Type: cross Abstract: Graph-based Retrieval-Augmented Generation (GraphRAG) advances flat document retrieval by structuring knowledge as relational graphs, enabling more coherent and effective reasoning. However, applying it to specific domains like legal reasoning faces critical challenges. (i) Legal corpora are heterogeneous, containing multi-granular knowledge from cases, articles and interpretations. A flat knowledge graph cannot adequately differentiate between factual details, applied rules, and abstract principles, limiting accurate retrieval. (ii) Reliable legal judgment demands transparent, evidence-based reasoning. Traditional RAG passes retrieved context directly to an LLM without verification, resulting in opaque, error-prone reasoning. To this end, we propose LegalGraphRAG, a framework designed for reliable legal reasoning. Our approach introduces two core components: a hierarchical legal graph that hierarchically organizes legal sources to enable retrieval at appropriate abstraction levels, and a multi-agent system for reliable legal reasoning, where a Researcher retrieves candidate evidence, an Auditor rigorously verifies its validity against source documents, and an Adjudicator synthesizes the set of verified evidence to render a final judgment. Extensive experiments show that LegalGraphRAG achieves the state-of-the-art performance, outperforming existing GraphRAG baselines in accurate and trustworthy legal analysis. Our code, datasets and implementation details are available at https://github.com/XMUDeepLIT/LegalGraphRAG.