构建法律咨询数据集与多智能体框架，提升法律问答的推理准确性。
From Query to Counsel: Structured Reasoning with a Multi-Agent Framework and Dataset for Legal Consultation
- 将法律问题分解为实体、事件、意图等构成的法律要素图，实现结构化推理。
- 在4.3万条真实法律咨询上训练，性能超越通用和法律大模型。
- 适合法律AI研发者、司法智能化项目团队参考使用。
法律咨询问答（Legal CQA）相比传统法律问答任务面临高质量训练数据稀缺、任务复杂度高及强上下文依赖等问题。为此，我们构建了包含超过43,000条真实中文法律咨询的大型数据集JurisCQAD，每条查询均配有专家验证的正负回答；设计了一种结构化任务分解方法，将每个查询转化为整合实体、事件、意图和法律问题的法律要素图。进一步提出JurisMA多智能体框架，支持动态路由、法条依据锚定与风格优化。结合要素图，该框架实现强上下文感知推理，有效捕捉法律事实、规范与程序逻辑间的依赖关系。在JurisCQAD上训练并在精炼版LawBench上评估，系统在多项词汇与语义指标上显著优于通用及法律领域大模型，证明了可解释性分解与模块化协作在Legal CQA中的优势。
原文摘要 · Abstract (English)
Legal consultation question answering (Legal CQA) presents unique challenges compared to traditional legal QA tasks, including the scarcity of high-quality training data, complex task composition, and strong contextual dependencies. To address these, we construct JurisCQAD, a large-scale dataset of over 43,000 real-world Chinese legal queries annotated with expert-validated positive and negative responses, and design a structured task decomposition that converts each query into a legal element graph integrating entities, events, intents, and legal issues. We further propose JurisMA, a modular multi-agent framework supporting dynamic routing, statutory grounding, and stylistic optimization. Combined with the element graph, the framework enables strong context-aware reasoning, effectively capturing dependencies across legal facts, norms, and procedural logic. Trained on JurisCQAD and evaluated on a refined LawBench, our system significantly outperforms both general-purpose and legal-domain LLMs across multiple lexical and semantic metrics, demonstrating the benefits of interpretable decomposition and modular collaboration in Legal CQA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。