@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2025-corag">
<titleInfo>
<title>CoRAG: Enhancing Hybrid Retrieval-Augmented Generation through a Cooperative Retriever Architecture</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zaiyi</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Song</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zihan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaochen</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinhan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liangjie</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jundong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">zheng-etal-2025-corag</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.872</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.872/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>16088</start>
<end>16101</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoRAG: Enhancing Hybrid Retrieval-Augmented Generation through a Cooperative Retriever Architecture
%A Zheng, Zaiyi
%A Wang, Song
%A Chen, Zihan
%A Zhu, Yaochen
%A He, Yinhan
%A Hong, Liangjie
%A Guo, Qi
%A Li, Jundong
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F zheng-etal-2025-corag
%X 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.
%R 10.18653/v1/2025.findings-emnlp.872
%U https://aclanthology.org/2025.findings-emnlp.872/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.872
%P 16088-16101
Markdown (Informal)
[CoRAG: Enhancing Hybrid Retrieval-Augmented Generation through a Cooperative Retriever Architecture](https://aclanthology.org/2025.findings-emnlp.872/) (Zheng et al., Findings 2025)
ACL
- Zaiyi Zheng, Song Wang, Zihan Chen, Yaochen Zhu, Yinhan He, Liangjie Hong, Qi Guo, and Jundong Li. 2025. CoRAG: Enhancing Hybrid Retrieval-Augmented Generation through a Cooperative Retriever Architecture. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 16088–16101, Suzhou, China. Association for Computational Linguistics.