让大模型按认知难度分层处理问题，减少错误和矛盾答案。
CogRAG: Tackling Heterogeneous Cognitive Demands in RAG via Stratified Retrieval and Reasoning
- 根据问题认知难度分层检索与推理，动态调整处理方式。
- 在营养师考试中将模型准确率从73.4%提升至85.8%。
- 无需训练，适配复杂专业任务，提升推理一致性。
检索增强生成（RAG）系统通常对所有查询采用统一流程，忽视不同任务的认知差异。这种认知盲区导致两类失效：低级事实缺失引发推理幻觉，高级分析任务中推理与答案不一致。我们提出CogRAG，一种无需训练、跨领域的分层认知框架，通过认知负载预测协调两个模块：认知自适应证据精炼，通过事实或选项导向路径补全信息；认知分层结构化推理，以对齐认知层级的模板替代自由链式思考。我们在注册营养师资格考试这一高难度专业测试集上评估，CogRAG显著降低早期事实错误，消除推理-答案不一致，使Qwen3-8B在单选模式下准确率从73.4%提升至85.8%，情景模式下从63.3%提升至80.5%。结果表明，认知分层控制是实现大模型可靠复杂推理的有效通用范式。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) frameworks typically process all queries through a one-size-fits-all pipeline, ignoring the heterogeneous cognitive demands of different tasks. This cognitive-blind approach causes two failure modes: cascading errors when low-level factual gaps trigger hallucinated reasoning, and reasoning-answer inconsistency in higher-order analytical tasks. We introduce CogRAG, a training-free, domain-agnostic framework that tackles these heterogeneous cognitive demands via stratified retrieval and reasoning. Inspired by Bloom's Taxonomy, CogRAG uses the predicted cognitive load of a query as a central control signal that coordinates two modules: Cognition-Adaptive Evidence Refinement supplements missing context via fact-centric or option-centric paths, and Cognition-Stratified Structured Reasoning replaces unconstrained chain-of-thought with cognition-aligned reasoning templates. We evaluate CogRAG on a demanding professional testbed, the Registered Dietitian qualification examination. CogRAG effectively reduces early-stage factual errors and eliminates reasoning-answer inconsistency, raising Qwen3-8B accuracy from 73.4\% to 85.8\% in single-choice mode and from 63.3\% to 80.5\% in scenario mode. These results highlight cognitive-stratified control as an effective, generalizable paradigm for reliable complex reasoning in large language models.
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。