@inproceedings{wei-etal-2026-arthopqa,
title = "{A}rt{H}op{QA}: Diagnosing Hidden-Chain Recovery in Artwork Question Answering",
author = "Wei, Xuefeng and
Zhou, Xuan and
Kato, Yuta and
Ozaki, Shintaro and
Hayashi, Kazuki and
Sakai, Yusuke and
Kamigaito, Hidetaka and
Hayashi, Katsuhiko and
Watanabe, Taro",
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.182/",
pages = "4057--4075",
ISBN = "979-8-89176-439-2",
abstract = "Many artwork questions begin with vision but cannot be answered by visual recognition alone. A model may need to connect an artwork to its creator, depicted subject, collection, or location, and then follow multiple facts to reach the answer. We introduce ArtHopQA, a multimodal multi-hop question answering benchmark for artwork understanding, containing 4,885 image-grounded questions paired with supporting fact chains. Experiments with open and API large vision-language models show a large gap: even the strongest open model reaches only 36.87{\%} accuracy when given the image and title, while gold-path performance reaches 97.77{\%} to 99.80{\%} when the supporting fact chain is provided. Text-only language models exhibit a similar gap, showing that the difficulty is not confined to visual input. Further analysis reveals high-prior geographic guesses, inconsistent answers under image-title conflict, and limited recovery of intermediate entities even when final answers are correct."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wei-etal-2026-arthopqa">
<titleInfo>
<title>ArtHopQA: Diagnosing Hidden-Chain Recovery in Artwork Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuefeng</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuta</namePart>
<namePart type="family">Kato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shintaro</namePart>
<namePart type="family">Ozaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazuki</namePart>
<namePart type="family">Hayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Sakai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidetaka</namePart>
<namePart type="family">Kamigaito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsuhiko</namePart>
<namePart type="family">Hayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</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>Many artwork questions begin with vision but cannot be answered by visual recognition alone. A model may need to connect an artwork to its creator, depicted subject, collection, or location, and then follow multiple facts to reach the answer. We introduce ArtHopQA, a multimodal multi-hop question answering benchmark for artwork understanding, containing 4,885 image-grounded questions paired with supporting fact chains. Experiments with open and API large vision-language models show a large gap: even the strongest open model reaches only 36.87% accuracy when given the image and title, while gold-path performance reaches 97.77% to 99.80% when the supporting fact chain is provided. Text-only language models exhibit a similar gap, showing that the difficulty is not confined to visual input. Further analysis reveals high-prior geographic guesses, inconsistent answers under image-title conflict, and limited recovery of intermediate entities even when final answers are correct.</abstract>
<identifier type="citekey">wei-etal-2026-arthopqa</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.182/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>4057</start>
<end>4075</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ArtHopQA: Diagnosing Hidden-Chain Recovery in Artwork Question Answering
%A Wei, Xuefeng
%A Zhou, Xuan
%A Kato, Yuta
%A Ozaki, Shintaro
%A Hayashi, Kazuki
%A Sakai, Yusuke
%A Kamigaito, Hidetaka
%A Hayashi, Katsuhiko
%A Watanabe, Taro
%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 wei-etal-2026-arthopqa
%X Many artwork questions begin with vision but cannot be answered by visual recognition alone. A model may need to connect an artwork to its creator, depicted subject, collection, or location, and then follow multiple facts to reach the answer. We introduce ArtHopQA, a multimodal multi-hop question answering benchmark for artwork understanding, containing 4,885 image-grounded questions paired with supporting fact chains. Experiments with open and API large vision-language models show a large gap: even the strongest open model reaches only 36.87% accuracy when given the image and title, while gold-path performance reaches 97.77% to 99.80% when the supporting fact chain is provided. Text-only language models exhibit a similar gap, showing that the difficulty is not confined to visual input. Further analysis reveals high-prior geographic guesses, inconsistent answers under image-title conflict, and limited recovery of intermediate entities even when final answers are correct.
%U https://aclanthology.org/2026.aacl-long.182/
%P 4057-4075
Markdown (Informal)
[ArtHopQA: Diagnosing Hidden-Chain Recovery in Artwork Question Answering](https://aclanthology.org/2026.aacl-long.182/) (Wei et al., AACL-IJCNLP 2026)
ACL
- Xuefeng Wei, Xuan Zhou, Yuta Kato, Shintaro Ozaki, Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, and Taro Watanabe. 2026. ArtHopQA: Diagnosing Hidden-Chain Recovery in Artwork Question Answering. 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 1: Long Papers), pages 4057–4075, Hengqin, China. Association for Computational Linguistics.