让大模型像人一样连点成线，解决知识碎片化问题
CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning
- 受双系统学习启发，将检索从查表升级为主动联想
- 在GraphRAG-Bench上检索召回率提升7-10%，生成准确率提升3-11%
- 适合需要逻辑推理和事实一致性的复杂任务
大型语言模型在知识密集型任务中因幻觉和信息分散导致推理断裂。尽管检索增强生成（RAG）能依托外部源，但现有方法多将证据视为孤立单元，无法重建逻辑链条。受互补学习系统（CLS）启发，我们提出CodaRAG框架，将检索从被动查询进化为主动关联发现。该框架采用三阶段流程：(1) 知识整合，将零散提取统一为稳定记忆基底；(2) 关联导航，通过语义、上下文与功能多维路径显式恢复分散证据链；(3) 干扰消除，剔除过度关联噪声，确保推理上下文连贯高精度。在GraphRAG-Bench上，CodaRAG实现检索召回率绝对提升7-10%，生成准确率提升3-11%，验证其在事实性、推理与创造性任务中系统性增强关联证据检索的能力。
原文摘要 · Abstract (English)
Large Language Models (LLMs) struggle with knowledge-intensive tasks due to hallucinations and fragmented reasoning over dispersed information. While Retrieval-Augmented Generation (RAG) grounds generation in external sources, existing methods often treat evidence as isolated units, failing to reconstruct the logical chains that connect these dots. Inspired by Complementary Learning Systems (CLS), we propose CodaRAG, a framework that evolves retrieval from passive lookup into active associative discovery. CodaRAG operates via a three-stage pipeline: (1) Knowledge Consolidation to unify fragmented extractions into a stable memory substrate; (2) Associative Navigation to traverse the graph via multi-dimensional pathways-semantic, contextualized, and functional-explicitly recovering dispersed evidence chains; and (3) Interference Elimination to prune hyper-associative noise, ensuring a coherent, high-precision reasoning context. On GraphRAG-Bench, CodaRAG achieves absolute gains of 7-10% in retrieval recall and 3-11% in generation accuracy. These results demonstrate CodaRAG's superior ability to systematically robustify associative evidence retrieval for factual, reasoning, and creative tasks.
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。