@inproceedings{zheng-etal-2025-corag,
    title = "{C}o{RAG}: Enhancing Hybrid Retrieval-Augmented Generation through a Cooperative Retriever Architecture",
    author = "Zheng, Zaiyi  and
      Wang, Song  and
      Chen, Zihan  and
      Zhu, Yaochen  and
      He, Yinhan  and
      Hong, Liangjie  and
      Guo, Qi  and
      Li, Jundong",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.872/",
    doi = "10.18653/v1/2025.findings-emnlp.872",
    pages = "16088--16101",
    ISBN = "979-8-89176-335-7",
    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. 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."
}