LEGO: Synergizing Expert GraphRAG and Expert Chain-of-Thought for Legal Reasoning

LEGO：协同专家图检索增强生成（GraphRAG）与专家思维链（CoT）进行法律推理

Large language models are increasingly applied to high-risk domains such as law, yet complex legal reasoning remains limited by two structural challenges. First, existing RAG and GraphRAG methods emphasize lexical or semantic similarity while overlooking normative relations among legal provisions. Second, vanilla Chain-of-Thought prompting may generate plausible rationales without enforcing the normative structure of legal reasoning. 大型语言模型正越来越多地应用于法律等高风险领域，然而复杂的法律推理仍受限于两个结构性挑战。首先，现有的检索增强生成（RAG）和图检索增强生成（GraphRAG）方法侧重于词汇或语义相似度，却忽视了法律条文之间的规范性关系。其次，基础的思维链（Chain-of-Thought）提示可能会生成看似合理的理由，却无法强制执行法律推理的规范性结构。

To deal with the bottleneck of pipelines in the legal reasoning domain, we propose LEGO, a dual-module framework that synergizes Legal Expert GraphRAG and expert Chain-of-thought for complex legal reasoning. ExpertGraphRAG uses an expert-annotated civil code graph encoding these normative relations with a greedy normative-coverage retrieval algorithm to dynamically extract instance-specific provision subgraphs, while ExpertCoT organizes the retrieved provisions and case facts into structured Provision-Fact-Conclusion reasoning. 为了解决法律推理领域流水线的瓶颈，我们提出了 LEGO，这是一个双模块框架，协同了法律专家图检索（Legal Expert GraphRAG）和专家思维链（Expert CoT）以进行复杂的法律推理。ExpertGraphRAG 使用专家标注的民法典图谱来编码这些规范性关系，并结合贪婪的规范覆盖检索算法，动态提取特定案例的条文子图；而 ExpertCoT 则将检索到的条文和案件事实组织成结构化的“条文-事实-结论”推理过程。

With a Qwen3-8B backbone, LEGO achieves 40.53% exact-match accuracy on LawExamQA_Civil, outperforming the evaluated RAG and CoT baselines and performing comparably to the evaluated larger models, while remaining robust on multi-hop questions. It also achieves the best results among the evaluated baselines on the open-ended benchmarks. Ablation studies confirm the individual and complementary contributions of both modules, demonstrating LEGO’s effectiveness in improving LLMs’ complex legal reasoning ability. 基于 Qwen3-8B 模型，LEGO 在 LawExamQA_Civil 数据集上达到了 40.53% 的精确匹配准确率，优于所评估的 RAG 和 CoT 基线模型，表现与所评估的更大规模模型相当，同时在多跳问题上保持了稳健性。它在开放式基准测试中也取得了所有评估基线中的最佳结果。消融实验证实了两个模块各自的贡献及其互补性，证明了 LEGO 在提升大语言模型复杂法律推理能力方面的有效性。