aiqbench analysis
This paper introduces CoAL-RAG, an adaptive retrieval method for legal AI that dynamically selects between semantic and keyword strategies based on question complexity to balance answer quality and efficiency. By quantifying reasoning demands through logical structure analysis, the approach significantly outperforms baseline models on both Chinese and English legal benchmarks while improving interpretability in high-risk scenarios. The work advances practical RAG architectures by addressing the trade-off between over-reasoning simple queries and ensuring deep logic for complex ones.
CoAL-RAG: A Complexity-Aware Legal Retrieval-Augmented Generation Method
arXiv:2608.17536v1 Announce Type: new Abstract: 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.
Abstract: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.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2608.17536 [cs.CL]
(or arXiv:2608.17536v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2608.17536 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 288 words
Related coverage
LiveLaw Supreme Court Half-Yearly Digest: January - June 2026 [Part 2]
livelaw.in · Sep 13, 2026
If This Were a Test, How Much Would It Cost?
LessWrong · Jun 16, 2026
RAGOCR: Optical Compression of Retrieval-Augmented Text via Visual Representation
arXiv · Aug 4, 2026
Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning
arXiv · Jun 12, 2026