CoRAG: Enhancing Hybrid Retrieval-Augmented Generation through a Cooperative Retriever Architecture
CoRAG dynamically selects textual or graph retrieval and blends results for global hybrid knowledge access, outperforming local hybrid RAG on QA benchmarks.
Published 2025Paper ↗
Only vote on papers you've read. Sign in with GitHub to vote.
CoRAG delivers strong hybrid retrieval gains by blending global semantic scoring with cooperative graph exploration, though its cooperation mechanism demands rigorous ablation to prove it integrates distant evidence rather than masking local retrieval with reranked neighbors.
Abstract
Retrieval-Augmented Generation (RAG) is introduced to enhance Large Language Models (LLMs) by integrating external knowledge.However, conventional RAG approaches treat retrieved documents as independent units, often overlooking their interdependencies.Hybrid-RAG, a recently proposed paradigm that combines textual documents and graph-structured relational information for RAG, mitigates this limitation by collecting entity documents during graph traversal.However, existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base, which often miss relevant information located further away from a global view.To overcome the above challenges, we propose CoRAG that dynamically chooses whether to retrieve information through direct textual search or explore graph structures in the knowledge base. 1 Our architecture blends different retrieval results, ensuring the potentially correct answer is chosen based on the query context.The textual retrieval components also enable global retrieval by scoring non-neighboring entity documents based on semantic relevance, bypassing the locality constraints of graph traversal.Experiments on semi-structured (relational and textual) knowledge base QA benchmarks demonstrate the outstanding performance of CoRAG.