@inproceedings{lee-etal-2025-hybgrag,
title = "{H}yb{GRAG}: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases",
author = "Lee, Meng-Chieh and
Zhu, Qi and
Mavromatis, Costas and
Han, Zhen and
Adeshina, Soji and
Ioannidis, Vassilis N. and
Rangwala, Huzefa and
Faloutsos, Christos",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.43/",
doi = "10.18653/v1/2025.acl-long.43",
pages = "879--893",
ISBN = "979-8-89176-251-0",
abstract = "Given a semi-structured knowledge base (SKB), where text documents are interconnected by relations, how can we effectively retrieve relevant information to answer user questions?Retrieval-Augmented Generation (RAG) retrieves documents to assist large language models (LLMs) in question answering; while Graph RAG (GRAG) uses structured knowledge bases as its knowledge source.However, many questions require both textual and relational information from SKB {---} referred to as ``hybrid'' questions {---} which complicates the retrieval process and underscores the need for a hybrid retrieval method that leverages both information.In this paper, through our empirical analysis, we identify key insights that show why existing methods may struggle with hybrid question answering (HQA) over SKB. Based on these insights, we propose HybGRAG for HQA, consisting of a retriever bank and a critic module, with the following advantages:1. Agentic, it automatically refines the output by incorporating feedback from the critic module, 2. Adaptive, it solves hybrid questions requiring both textual and relational information with the retriever bank,3. Interpretable, it justifies decision making with intuitive refinement path, and4. Effective, it surpasses all baselines on HQA benchmarks.In experiments on the STaRK benchmark, HybGRAG achieves significant performance gains, with an average relative improvement in Hit@1 of 51{\%}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2025-hybgrag">
<titleInfo>
<title>HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases</title>
</titleInfo>
<name type="personal">
<namePart type="given">Meng-Chieh</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Costas</namePart>
<namePart type="family">Mavromatis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soji</namePart>
<namePart type="family">Adeshina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vassilis</namePart>
<namePart type="given">N</namePart>
<namePart type="family">Ioannidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huzefa</namePart>
<namePart type="family">Rangwala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Faloutsos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Given a semi-structured knowledge base (SKB), where text documents are interconnected by relations, how can we effectively retrieve relevant information to answer user questions?Retrieval-Augmented Generation (RAG) retrieves documents to assist large language models (LLMs) in question answering; while Graph RAG (GRAG) uses structured knowledge bases as its knowledge source.However, many questions require both textual and relational information from SKB — referred to as “hybrid” questions — which complicates the retrieval process and underscores the need for a hybrid retrieval method that leverages both information.In this paper, through our empirical analysis, we identify key insights that show why existing methods may struggle with hybrid question answering (HQA) over SKB. Based on these insights, we propose HybGRAG for HQA, consisting of a retriever bank and a critic module, with the following advantages:1. Agentic, it automatically refines the output by incorporating feedback from the critic module, 2. Adaptive, it solves hybrid questions requiring both textual and relational information with the retriever bank,3. Interpretable, it justifies decision making with intuitive refinement path, and4. Effective, it surpasses all baselines on HQA benchmarks.In experiments on the STaRK benchmark, HybGRAG achieves significant performance gains, with an average relative improvement in Hit@1 of 51%.</abstract>
<identifier type="citekey">lee-etal-2025-hybgrag</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.43</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.43/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>879</start>
<end>893</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases
%A Lee, Meng-Chieh
%A Zhu, Qi
%A Mavromatis, Costas
%A Han, Zhen
%A Adeshina, Soji
%A Ioannidis, Vassilis N.
%A Rangwala, Huzefa
%A Faloutsos, Christos
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F lee-etal-2025-hybgrag
%X Given a semi-structured knowledge base (SKB), where text documents are interconnected by relations, how can we effectively retrieve relevant information to answer user questions?Retrieval-Augmented Generation (RAG) retrieves documents to assist large language models (LLMs) in question answering; while Graph RAG (GRAG) uses structured knowledge bases as its knowledge source.However, many questions require both textual and relational information from SKB — referred to as “hybrid” questions — which complicates the retrieval process and underscores the need for a hybrid retrieval method that leverages both information.In this paper, through our empirical analysis, we identify key insights that show why existing methods may struggle with hybrid question answering (HQA) over SKB. Based on these insights, we propose HybGRAG for HQA, consisting of a retriever bank and a critic module, with the following advantages:1. Agentic, it automatically refines the output by incorporating feedback from the critic module, 2. Adaptive, it solves hybrid questions requiring both textual and relational information with the retriever bank,3. Interpretable, it justifies decision making with intuitive refinement path, and4. Effective, it surpasses all baselines on HQA benchmarks.In experiments on the STaRK benchmark, HybGRAG achieves significant performance gains, with an average relative improvement in Hit@1 of 51%.
%R 10.18653/v1/2025.acl-long.43
%U https://aclanthology.org/2025.acl-long.43/
%U https://doi.org/10.18653/v1/2025.acl-long.43
%P 879-893
Markdown (Informal)
[HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases](https://aclanthology.org/2025.acl-long.43/) (Lee et al., ACL 2025)
ACL
- Meng-Chieh Lee, Qi Zhu, Costas Mavromatis, Zhen Han, Soji Adeshina, Vassilis N. Ioannidis, Huzefa Rangwala, and Christos Faloutsos. 2025. HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 879–893, Vienna, Austria. Association for Computational Linguistics.