@inproceedings{yuan-etal-2026-routerkgqa,
title = "{R}outer{KGQA}: Specialized{--}General Model Routing for Constraint-Aware Knowledge Graph Question Answering",
author = "Yuan, Bo and
Deng, Hexuan and
Bang, Long and
Liu, Xuebo and
Shuai, Zheng and
Mingzhen, Zhou and
Zhang, Min",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.87/",
pages = "1903--1924",
ISBN = "979-8-89176-439-2",
abstract = "Knowledge graph question answering (KGQA) is a promising approach for mitigating LLM hallucination by grounding reasoning in structured and verifiable knowledge graphs. Existing approaches fall into two paradigms: retrieval-based methods utilize small specialized models, which are efficient but often produce unreachable paths and miss implicit constraints, while agent-based methods utilize large general models, which achieve stronger structural grounding at substantially higher cost. We propose RouterKGQA, a framework for specialized{--}general model collaboration, in which a specialized model generates reasoning paths and a general model performs KG-guided repair only when needed, improving performance at minimal cost. We further equip the specialized model with constraint-aware answer filtering, which reduces redundant answers. In addition, we design a more efficient general agent workflow, further lowering inference cost. Experimental results show that RouterKGQA outperforms the previous best by 3.57 points in F1 and 0.49 points in Hits@1 on average across benchmarks, while requiring only 1.15 LLM calls per question on WebQSP (1.23 on CWQ). Code and models are available at https://github.com/Oldcircle/RouterKGQA."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yuan-etal-2026-routerkgqa">
<titleInfo>
<title>RouterKGQA: Specialized–General Model Routing for Constraint-Aware Knowledge Graph Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hexuan</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Long</namePart>
<namePart type="family">Bang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuebo</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Shuai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Mingzhen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Knowledge graph question answering (KGQA) is a promising approach for mitigating LLM hallucination by grounding reasoning in structured and verifiable knowledge graphs. Existing approaches fall into two paradigms: retrieval-based methods utilize small specialized models, which are efficient but often produce unreachable paths and miss implicit constraints, while agent-based methods utilize large general models, which achieve stronger structural grounding at substantially higher cost. We propose RouterKGQA, a framework for specialized–general model collaboration, in which a specialized model generates reasoning paths and a general model performs KG-guided repair only when needed, improving performance at minimal cost. We further equip the specialized model with constraint-aware answer filtering, which reduces redundant answers. In addition, we design a more efficient general agent workflow, further lowering inference cost. Experimental results show that RouterKGQA outperforms the previous best by 3.57 points in F1 and 0.49 points in Hits@1 on average across benchmarks, while requiring only 1.15 LLM calls per question on WebQSP (1.23 on CWQ). Code and models are available at https://github.com/Oldcircle/RouterKGQA.</abstract>
<identifier type="citekey">yuan-etal-2026-routerkgqa</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.87/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1903</start>
<end>1924</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RouterKGQA: Specialized–General Model Routing for Constraint-Aware Knowledge Graph Question Answering
%A Yuan, Bo
%A Deng, Hexuan
%A Bang, Long
%A Liu, Xuebo
%A Shuai, Zheng
%A Mingzhen, Zhou
%A Zhang, Min
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F yuan-etal-2026-routerkgqa
%X Knowledge graph question answering (KGQA) is a promising approach for mitigating LLM hallucination by grounding reasoning in structured and verifiable knowledge graphs. Existing approaches fall into two paradigms: retrieval-based methods utilize small specialized models, which are efficient but often produce unreachable paths and miss implicit constraints, while agent-based methods utilize large general models, which achieve stronger structural grounding at substantially higher cost. We propose RouterKGQA, a framework for specialized–general model collaboration, in which a specialized model generates reasoning paths and a general model performs KG-guided repair only when needed, improving performance at minimal cost. We further equip the specialized model with constraint-aware answer filtering, which reduces redundant answers. In addition, we design a more efficient general agent workflow, further lowering inference cost. Experimental results show that RouterKGQA outperforms the previous best by 3.57 points in F1 and 0.49 points in Hits@1 on average across benchmarks, while requiring only 1.15 LLM calls per question on WebQSP (1.23 on CWQ). Code and models are available at https://github.com/Oldcircle/RouterKGQA.
%U https://aclanthology.org/2026.aacl-long.87/
%P 1903-1924
Markdown (Informal)
[RouterKGQA: Specialized–General Model Routing for Constraint-Aware Knowledge Graph Question Answering](https://aclanthology.org/2026.aacl-long.87/) (Yuan et al., AACL-IJCNLP 2026)
ACL