@inproceedings{sei-etal-2026-training,
title = "Training-Free Residual-Guided Retrieval for Multi-hop {KGQA} with Single-Step {LLM} Inference",
author = "Sei, Keito and
Maurya, Sunil Kumar and
Kobashi, Yohei and
Matsuo, Yutaka",
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 2: Short Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-short.29/",
pages = "430--442",
ISBN = "979-8-89176-440-8",
abstract = "Graph-based retrieval is effective for knowledge graph question answering (KGQA), but retrieving the correct reasoning path remains challenging in multi-hop settings because the retrieval objective changes as reasoning progresses. Existing methods often address this issue with repeated LLM-based planning, which improves adaptivity but increases inference cost. We present a training-free residual-guided retrieval framework that updates the retrieval signal according to the current reasoning path in embedding space. The method performs multi-hop graph retrieval without repeated hop-wise LLM calls and invokes the LLM only once for final answer generation. Experiments on WebQSP and CWQ show that our method achieves superior Hit rates with only a single LLM call. Additional comparisons with supervised graph-based KGQA methods show that the proposed method remains effective without task-specific training data. These results suggest that residual-guided retrieval is an efficient alternative for multi-hop graph-based question answering."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sei-etal-2026-training">
<titleInfo>
<title>Training-Free Residual-Guided Retrieval for Multi-hop KGQA with Single-Step LLM Inference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keito</namePart>
<namePart type="family">Sei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunil</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Maurya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yohei</namePart>
<namePart type="family">Kobashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutaka</namePart>
<namePart type="family">Matsuo</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 2: Short 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">979-8-89176-440-8</identifier>
</relatedItem>
<abstract>Graph-based retrieval is effective for knowledge graph question answering (KGQA), but retrieving the correct reasoning path remains challenging in multi-hop settings because the retrieval objective changes as reasoning progresses. Existing methods often address this issue with repeated LLM-based planning, which improves adaptivity but increases inference cost. We present a training-free residual-guided retrieval framework that updates the retrieval signal according to the current reasoning path in embedding space. The method performs multi-hop graph retrieval without repeated hop-wise LLM calls and invokes the LLM only once for final answer generation. Experiments on WebQSP and CWQ show that our method achieves superior Hit rates with only a single LLM call. Additional comparisons with supervised graph-based KGQA methods show that the proposed method remains effective without task-specific training data. These results suggest that residual-guided retrieval is an efficient alternative for multi-hop graph-based question answering.</abstract>
<identifier type="citekey">sei-etal-2026-training</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-short.29/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>430</start>
<end>442</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Training-Free Residual-Guided Retrieval for Multi-hop KGQA with Single-Step LLM Inference
%A Sei, Keito
%A Maurya, Sunil Kumar
%A Kobashi, Yohei
%A Matsuo, Yutaka
%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 2: Short Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-440-8
%F sei-etal-2026-training
%X Graph-based retrieval is effective for knowledge graph question answering (KGQA), but retrieving the correct reasoning path remains challenging in multi-hop settings because the retrieval objective changes as reasoning progresses. Existing methods often address this issue with repeated LLM-based planning, which improves adaptivity but increases inference cost. We present a training-free residual-guided retrieval framework that updates the retrieval signal according to the current reasoning path in embedding space. The method performs multi-hop graph retrieval without repeated hop-wise LLM calls and invokes the LLM only once for final answer generation. Experiments on WebQSP and CWQ show that our method achieves superior Hit rates with only a single LLM call. Additional comparisons with supervised graph-based KGQA methods show that the proposed method remains effective without task-specific training data. These results suggest that residual-guided retrieval is an efficient alternative for multi-hop graph-based question answering.
%U https://aclanthology.org/2026.aacl-short.29/
%P 430-442
Markdown (Informal)
[Training-Free Residual-Guided Retrieval for Multi-hop KGQA with Single-Step LLM Inference](https://aclanthology.org/2026.aacl-short.29/) (Sei et al., AACL-IJCNLP 2026)
ACL
- Keito Sei, Sunil Kumar Maurya, Yohei Kobashi, and Yutaka Matsuo. 2026. Training-Free Residual-Guided Retrieval for Multi-hop KGQA with Single-Step LLM Inference. In 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 2: Short Papers), pages 430–442, Hengqin, China. Association for Computational Linguistics.