LEGO：融合专家GraphRAG与专家思维链的司法推理方法
LEGO: Synergizing Expert GraphRAG and Expert Chain-of-Thought for Legal Reasoning
浏览论文内容
中文总结 AI 辅助
提出LEGO双模块框架，结合法律专家GraphRAG和专家思维链，通过规范关系编码和结构化推理，在LawExamQA_Civil上取得40.53%精确匹配准确率，提升复杂法律推理能力。
中文摘要 AI 辅助
大型语言模型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RAG和GraphRAG方法强调词汇或语义相似性，却忽视了法律条文之间的规范关系。其次，普通的思维链提示可能生成看似合理的推理过程，却未强制遵循法律推理的规范结构。为解决法律推理领域流程的瓶颈，我们提出LEGO，一个双模块框架，将法律专家GraphRAG与专家思维链协同用于复杂法律推理。ExpertGraphRAG利用专家标注的民法典图，编码这些规范关系，并通过贪心规范覆盖检索算法动态提取针对具体实例的法条子图，而ExpertCoT将检索到的法条和案件事实组织为结构化的“法条-事实-结论”推理。基于Qwen3-8B骨干模型，LEGO在LawExamQA_Civil上达到40.53%的精确匹配准确率，优于所评估的RAG和CoT基线，并与所评估的更大模型表现相当，同时在多跳问题上保持稳健。在开放式基准上，它也取得了所评估基线中的最佳结果。消融研究证实了两个模块的独立及互补贡献，展示了LEGO在提升大型语言模型复杂法律推理能力方面的有效性。代码和数据集可在链接中找到：https://github.com/BLK-WHT/LEGO
英文摘要
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. 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. 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. Code and dataset can be found in the link: https://github.com/BLK-WHT/LEGO
发表机构
- Alma AI, University of Bologna（博洛尼亚大学 Alma AI）
- Tsinghua University（清华大学）
- Modelbest Inc.（Modelbest 公司）
- Xiamen University（厦门大学）
- Shanghai Jiao Tong University（上海交通大学）
机构由 AI 辅助整理，请以论文原文为准。
