@inproceedings{zhang-etal-2026-towards-holistic,
title = "Towards Holistic Knowledge Retrieval for Augmented Generation: Integrating Graph-Grounded and Query-Aligned Knowledge",
author = "Zhang, Weidong and
Wang, Zhe and
Wang, Kewen and
Guo, Haifeng and
Lian, Shuxuan and
Du, Weizhi",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.897/",
pages = "20661--20681",
ISBN = "979-8-89176-459-0",
abstract = "Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to access external knowledge during generation, improving factual reliability without parameter retraining. However, existing methods still struggle to retrieve evidence that is both relevant and complete. Standard RAG may miss semantic associations among related chunks. Graph-based RAG addresses this issue by modeling entity relations, but it is often query-agnostic. Question-format RAG further improves query matching by converting facts into Question-Answer (QA) pairs, but it cannot guarantee semantic association and introduces knowledge fragmentation. To address these issues, we propose HolisticRAG, a framework integrating graph-grounded and query-aligned knowledge for holistic knowledge RAG. In the offline stage, HolisticRAG constructs a knowledge representation to preserve semantic associations while reducing query-agnostic retrieval. In the online stage, it applies holistic knowledge clustering to merge all fragmented evidence and adaptively retrieve sufficient supporting facts. Experiments demonstrate the effiectiveness of HolisticRAG."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-towards-holistic">
<titleInfo>
<title>Towards Holistic Knowledge Retrieval for Augmented Generation: Integrating Graph-Grounded and Query-Aligned Knowledge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weidong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhe</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kewen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haifeng</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuxuan</namePart>
<namePart type="family">Lian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weizhi</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to access external knowledge during generation, improving factual reliability without parameter retraining. However, existing methods still struggle to retrieve evidence that is both relevant and complete. Standard RAG may miss semantic associations among related chunks. Graph-based RAG addresses this issue by modeling entity relations, but it is often query-agnostic. Question-format RAG further improves query matching by converting facts into Question-Answer (QA) pairs, but it cannot guarantee semantic association and introduces knowledge fragmentation. To address these issues, we propose HolisticRAG, a framework integrating graph-grounded and query-aligned knowledge for holistic knowledge RAG. In the offline stage, HolisticRAG constructs a knowledge representation to preserve semantic associations while reducing query-agnostic retrieval. In the online stage, it applies holistic knowledge clustering to merge all fragmented evidence and adaptively retrieve sufficient supporting facts. Experiments demonstrate the effiectiveness of HolisticRAG.</abstract>
<identifier type="citekey">zhang-etal-2026-towards-holistic</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.897/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>20661</start>
<end>20681</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Holistic Knowledge Retrieval for Augmented Generation: Integrating Graph-Grounded and Query-Aligned Knowledge
%A Zhang, Weidong
%A Wang, Zhe
%A Wang, Kewen
%A Guo, Haifeng
%A Lian, Shuxuan
%A Du, Weizhi
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F zhang-etal-2026-towards-holistic
%X Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to access external knowledge during generation, improving factual reliability without parameter retraining. However, existing methods still struggle to retrieve evidence that is both relevant and complete. Standard RAG may miss semantic associations among related chunks. Graph-based RAG addresses this issue by modeling entity relations, but it is often query-agnostic. Question-format RAG further improves query matching by converting facts into Question-Answer (QA) pairs, but it cannot guarantee semantic association and introduces knowledge fragmentation. To address these issues, we propose HolisticRAG, a framework integrating graph-grounded and query-aligned knowledge for holistic knowledge RAG. In the offline stage, HolisticRAG constructs a knowledge representation to preserve semantic associations while reducing query-agnostic retrieval. In the online stage, it applies holistic knowledge clustering to merge all fragmented evidence and adaptively retrieve sufficient supporting facts. Experiments demonstrate the effiectiveness of HolisticRAG.
%U https://aclanthology.org/2026.emnlp-main.897/
%P 20661-20681
Markdown (Informal)
[Towards Holistic Knowledge Retrieval for Augmented Generation: Integrating Graph-Grounded and Query-Aligned Knowledge](https://aclanthology.org/2026.emnlp-main.897/) (Zhang et al., EMNLP 2026)
ACL