@inproceedings{xu-etal-2026-query,
title = "Query-Aware Graph Attention for Precise Subgraph Retrieval in Knowledge-Augmented Reasoning",
author = "Xu, Yuanye and
Guo, Linyi and
Zhang, Yue and
Ning, Fu",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.398/",
pages = "8127--8148",
ISBN = "979-8-89176-395-1",
abstract = "Large language models (LLMs) increasingly rely on external knowledge to mitigate hallucinations, yet retrieving precise multi-hop evidence for knowledge-augmented reasoning remains difficult. Existing Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) systems insufficiently model the interaction between query semantics and relation types, resulting in imprecise subgraph retrieval and unstable reasoning. We propose Query-aware Subgraph Retrieval Augmented Generation (QSRAG), a retrieval framework built upon a Query-Relational Graph Attention Network (QR-GAT) that integrates query semantics and relation embeddings directly into the attention mechanism, enabling fine-grained triple scoring and scalable subgraph construction. This query{--}relation conditioning improves relevance estimation and suppresses noisy edges, producing faithful reasoning subgraphs. Experiments on WebQSP and CWQ establish new state-of-the-art results in both Triple Recall and Answer Recall, and significantly enhance LLMs reasoning accuracy without fine-tuning. These findings underscore the effectiveness of modeling query{--}relation interactions for reliable knowledge-augmented reasoning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2026-query">
<titleInfo>
<title>Query-Aware Graph Attention for Precise Subgraph Retrieval in Knowledge-Augmented Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuanye</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linyi</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fu</namePart>
<namePart type="family">Ning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Large language models (LLMs) increasingly rely on external knowledge to mitigate hallucinations, yet retrieving precise multi-hop evidence for knowledge-augmented reasoning remains difficult. Existing Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) systems insufficiently model the interaction between query semantics and relation types, resulting in imprecise subgraph retrieval and unstable reasoning. We propose Query-aware Subgraph Retrieval Augmented Generation (QSRAG), a retrieval framework built upon a Query-Relational Graph Attention Network (QR-GAT) that integrates query semantics and relation embeddings directly into the attention mechanism, enabling fine-grained triple scoring and scalable subgraph construction. This query–relation conditioning improves relevance estimation and suppresses noisy edges, producing faithful reasoning subgraphs. Experiments on WebQSP and CWQ establish new state-of-the-art results in both Triple Recall and Answer Recall, and significantly enhance LLMs reasoning accuracy without fine-tuning. These findings underscore the effectiveness of modeling query–relation interactions for reliable knowledge-augmented reasoning.</abstract>
<identifier type="citekey">xu-etal-2026-query</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.398/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>8127</start>
<end>8148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Query-Aware Graph Attention for Precise Subgraph Retrieval in Knowledge-Augmented Reasoning
%A Xu, Yuanye
%A Guo, Linyi
%A Zhang, Yue
%A Ning, Fu
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F xu-etal-2026-query
%X Large language models (LLMs) increasingly rely on external knowledge to mitigate hallucinations, yet retrieving precise multi-hop evidence for knowledge-augmented reasoning remains difficult. Existing Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) systems insufficiently model the interaction between query semantics and relation types, resulting in imprecise subgraph retrieval and unstable reasoning. We propose Query-aware Subgraph Retrieval Augmented Generation (QSRAG), a retrieval framework built upon a Query-Relational Graph Attention Network (QR-GAT) that integrates query semantics and relation embeddings directly into the attention mechanism, enabling fine-grained triple scoring and scalable subgraph construction. This query–relation conditioning improves relevance estimation and suppresses noisy edges, producing faithful reasoning subgraphs. Experiments on WebQSP and CWQ establish new state-of-the-art results in both Triple Recall and Answer Recall, and significantly enhance LLMs reasoning accuracy without fine-tuning. These findings underscore the effectiveness of modeling query–relation interactions for reliable knowledge-augmented reasoning.
%U https://aclanthology.org/2026.findings-acl.398/
%P 8127-8148
Markdown (Informal)
[Query-Aware Graph Attention for Precise Subgraph Retrieval in Knowledge-Augmented Reasoning](https://aclanthology.org/2026.findings-acl.398/) (Xu et al., Findings 2026)
ACL