发表机构
North China University of Technology; Beijing Key Laboratory of Key Technologies for AI+ Domain Applications; Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data（北方工业大学; 北京市AI+领域应用关键技术重点实验室; 大规模流数据集成与分析技术北京市重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对法律咨询问题复杂度差异带来的检索策略适配难题，提出CoAL-RAG方法，通过多维评估实现检索策略自适应，在中英文法律基准上均显著优于基线，兼顾生成质量、推理能力与效率。
AI 中文摘要
法律咨询问题呈现出多层次的复杂度，单一检索策略常导致简单问题推理过度、复杂问题可解释性差，难以满足高风险场景对答案质量与效率的双重要求。针对该问题，本文提出CoAL-RAG这一复杂度感知的法律检索增强生成方法，构建基于“问题本质”与“检索一致性”的多维评估机制，以实现检索策略的自适应路由。首先根据问题的逻辑结构量化推理需求，再利用语义检索与关键词检索的差异间接反映问题复杂度，从而选择最合适的检索策略并动态过滤上下文信息。实验结果表明，所提方法在中文法律基准数据集（SocialLawQA、LawBench）上显著优于基线模型，在英文数据集（LexGLUE、CaseHold）上也展现出较强的跨司法管辖区泛化能力。具体而言，在中文数据集上，BLEU分数提升42.5%，ROUGE-L达到基于知识图谱方法的3.6倍；在英文基准上，CoAL-RAG保持极具竞争力的准确率，在不同司法体系间实现了生成质量、深度逻辑推理与系统效率的最优平衡。
英文摘要
Legal consultation questions exhibit multi-level complexity. A single retrieval strategy often leads to over-reasoning for simple questions and poor interpretability for complex ones, making it difficult to meet the requirements for both answer quality and efficiency in high-risk scenarios. To address this issue, this paper proposes CoAL-RAG, a complexity-aware legal retrieval-augmented generation method, which constructs a multi-dimensional evaluation mechanism based on ``question essence'' and ``retrieval consistency'' to enable adaptive routing of retrieval strategies. First, the reasoning demand is quantified according to the logical structure of the question. Then, the discrepancy between semantic retrieval and keyword retrieval is utilized to indirectly reflect problem complexity, thereby selecting the most appropriate retrieval strategy and dynamically filtering contextual information. Experimental results demonstrate that the proposed method significantly outperforms baseline models not only on Chinese legal benchmarks (SocialLawQA, LawBench) but also demonstrates strong cross-jurisdictional generalization on English datasets (LexGLUE, CaseHold). Specifically, on Chinese datasets, the BLEU score improves by 42.5\% and ROUGE-L reaches 3.6 times that of knowledge graph-based methods. On English benchmarks, CoAL-RAG maintains highly competitive accuracy, achieving an optimal balance between generation quality, deep logical reasoning, and system efficiency across different legal systems.
Comments15 pages;accepted to ICSS 2026
