@inproceedings{tao-etal-2026-guiding,
title = "Guiding Graph: Explicit Query-Structure Guidance for Knowledge Graph Question Answering",
author = "Tao, Dehao and
Liu, Guangjie and
Zhou, Jun and
Chen, Junhao and
Zheng, Wei and
Chen, Rui and
Junren, Chen and
Huang, Yongfeng and
Jiang, Minghu",
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.2312/",
pages = "52549--52564",
ISBN = "979-8-89176-459-0",
abstract = "Large Language Models (LLMs) can match local semantic clues in knowledge graphs (KGs), but complex KGQA often requires satisfying the full dependency structure of a question. Existing retrieval-based methods therefore risk producing reasoning paths that look plausible at each step but violate the query{'}s global intent. We propose Guiding Graph, a schema-light query-structure interface that turns KGQA from open-ended semantic traversal into structure-constrained query completion. A Guiding Graph exposes the entities, placeholders, and global dependencies that KG exploration must preserve, serving as an operational interface between natural language and graph traversal. The interface is training-free by default through prompt-based construction, and can optionally be strengthened with a cold-start fine-tuned constructor trained from limited bootstrapped supervision. Given the constructed Guiding Graph, exploration is governed by target selection from the query structure, structure-guided pruning before semantic matching, and target-scoped semantic alignment under the current Guiding Graph triple. Experiments on WebQSP, CWQ, and a domain-specific agricultural KG show that explicit query-structure guidance improves accuracy, robustness, and efficiency, with especially clear benefits for multi-hop reasoning and smaller LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tao-etal-2026-guiding">
<titleInfo>
<title>Guiding Graph: Explicit Query-Structure Guidance for Knowledge Graph Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dehao</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guangjie</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junhao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Junren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongfeng</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghu</namePart>
<namePart type="family">Jiang</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>Large Language Models (LLMs) can match local semantic clues in knowledge graphs (KGs), but complex KGQA often requires satisfying the full dependency structure of a question. Existing retrieval-based methods therefore risk producing reasoning paths that look plausible at each step but violate the query’s global intent. We propose Guiding Graph, a schema-light query-structure interface that turns KGQA from open-ended semantic traversal into structure-constrained query completion. A Guiding Graph exposes the entities, placeholders, and global dependencies that KG exploration must preserve, serving as an operational interface between natural language and graph traversal. The interface is training-free by default through prompt-based construction, and can optionally be strengthened with a cold-start fine-tuned constructor trained from limited bootstrapped supervision. Given the constructed Guiding Graph, exploration is governed by target selection from the query structure, structure-guided pruning before semantic matching, and target-scoped semantic alignment under the current Guiding Graph triple. Experiments on WebQSP, CWQ, and a domain-specific agricultural KG show that explicit query-structure guidance improves accuracy, robustness, and efficiency, with especially clear benefits for multi-hop reasoning and smaller LLMs.</abstract>
<identifier type="citekey">tao-etal-2026-guiding</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2312/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>52549</start>
<end>52564</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Guiding Graph: Explicit Query-Structure Guidance for Knowledge Graph Question Answering
%A Tao, Dehao
%A Liu, Guangjie
%A Zhou, Jun
%A Chen, Junhao
%A Zheng, Wei
%A Chen, Rui
%A Junren, Chen
%A Huang, Yongfeng
%A Jiang, Minghu
%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 tao-etal-2026-guiding
%X Large Language Models (LLMs) can match local semantic clues in knowledge graphs (KGs), but complex KGQA often requires satisfying the full dependency structure of a question. Existing retrieval-based methods therefore risk producing reasoning paths that look plausible at each step but violate the query’s global intent. We propose Guiding Graph, a schema-light query-structure interface that turns KGQA from open-ended semantic traversal into structure-constrained query completion. A Guiding Graph exposes the entities, placeholders, and global dependencies that KG exploration must preserve, serving as an operational interface between natural language and graph traversal. The interface is training-free by default through prompt-based construction, and can optionally be strengthened with a cold-start fine-tuned constructor trained from limited bootstrapped supervision. Given the constructed Guiding Graph, exploration is governed by target selection from the query structure, structure-guided pruning before semantic matching, and target-scoped semantic alignment under the current Guiding Graph triple. Experiments on WebQSP, CWQ, and a domain-specific agricultural KG show that explicit query-structure guidance improves accuracy, robustness, and efficiency, with especially clear benefits for multi-hop reasoning and smaller LLMs.
%U https://aclanthology.org/2026.emnlp-main.2312/
%P 52549-52564
Markdown (Informal)
[Guiding Graph: Explicit Query-Structure Guidance for Knowledge Graph Question Answering](https://aclanthology.org/2026.emnlp-main.2312/) (Tao et al., EMNLP 2026)
ACL
- Dehao Tao, Guangjie Liu, Jun Zhou, Junhao Chen, Wei Zheng, Rui Chen, Chen Junren, Yongfeng Huang, and Minghu Jiang. 2026. Guiding Graph: Explicit Query-Structure Guidance for Knowledge Graph Question Answering. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 52549–52564, Budapest, Hungary. Association for Computational Linguistics.