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.

翻译：基于图的检索增强生成方法（GraphRAG）通过将知识结构化为关系图，突破了平面文档检索的局限，实现了更连贯且有效的推理。然而，将该方法应用于法律推理等特定领域仍面临关键挑战：（i）法律语料具有异质性，包含来自案例、法条及司法解释的多粒度知识。扁平化知识图谱难以有效区分事实细节、适用规则与抽象原则，从而制约了检索精度；（ii）可靠的法律判决要求透明且基于证据的推理。传统RAG方法将检索到的上下文直接传入大语言模型而不进行验证，导致推理过程不透明且易出错。为此，我们提出LegalGraphRAG——一个专为可靠法律推理设计的框架。该框架引入两个核心组件：层级化法律图谱（Hierarchical Legal Graph），通过层级化组织法律来源实现适宜抽象层面的检索；以及用于可靠法律推理的多智能体系统（Multi-Agent System），其中研究员（Researcher）负责检索候选证据，审计员（Auditor）严格验证证据在源文件中的有效性，裁判员（Adjudicator）整合已验证的证据集以作出最终判决。大量实验表明，LegalGraphRAG实现了最先进的性能，在准确且可信的法律分析中超越现有GraphRAG基线方法。我们的代码、数据集及实现细节详见 https://github.com/XMUDeepLIT/LegalGraphRAG。