@inproceedings{zhou-etal-2026-artkgc,
title = "{ARTKGC}: Leakage-Controlled Multimodal Knowledge Graph Completion for Artwork Explanation",
author = "Zhou, Xuan and
Wei, Xuefeng and
Kato, Yuta and
Ozaki, Shintaro and
Hayashi, Kazuki and
Sakai, Yusuke and
Kamigaito, Hidetaka and
Hayashi, Katsuhiko and
Watanabe, Taro",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2299/",
pages = "49291--49309",
ISBN = "979-8-89176-462-0",
abstract = "Explaining an artwork requires knowledge beyond visual recognition, including facts about its creator, subject, material, style, collection, and historical context. Knowledge graphs can provide such evidence, but artwork KGs are incomplete, especially for newly encountered artworks. We introduce ArtKGC, a leakage-controlled multimodal benchmark and evaluation protocol for artwork knowledge graph completion. ArtKGC links artworks to Wikidata facts, Wikipedia descriptions, and visual evidence while controlling ambiguous mappings, graph leakage, and descriptions that directly reveal held-out answers. We show that graph-only models are weak for unseen artworks, raw text can inflate evaluation through answer leakage, and visual evidence is strongly relation-dependent. As an interpretable diagnostic baseline, we use a validation-calibrated reranker that combines structural, sentence-redacted textual, and visual evidence. Experiments show improved completion in the primary inductive-artwork setting and modest downstream evidence gains for artwork QA and explanation diagnostics."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2026-artkgc">
<titleInfo>
<title>ARTKGC: Leakage-Controlled Multimodal Knowledge Graph Completion for Artwork Explanation</title>
</titleInfo>
<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">Xuefeng</namePart>
<namePart type="family">Wei</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>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Explaining an artwork requires knowledge beyond visual recognition, including facts about its creator, subject, material, style, collection, and historical context. Knowledge graphs can provide such evidence, but artwork KGs are incomplete, especially for newly encountered artworks. We introduce ArtKGC, a leakage-controlled multimodal benchmark and evaluation protocol for artwork knowledge graph completion. ArtKGC links artworks to Wikidata facts, Wikipedia descriptions, and visual evidence while controlling ambiguous mappings, graph leakage, and descriptions that directly reveal held-out answers. We show that graph-only models are weak for unseen artworks, raw text can inflate evaluation through answer leakage, and visual evidence is strongly relation-dependent. As an interpretable diagnostic baseline, we use a validation-calibrated reranker that combines structural, sentence-redacted textual, and visual evidence. Experiments show improved completion in the primary inductive-artwork setting and modest downstream evidence gains for artwork QA and explanation diagnostics.</abstract>
<identifier type="citekey">zhou-etal-2026-artkgc</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2299/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>49291</start>
<end>49309</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ARTKGC: Leakage-Controlled Multimodal Knowledge Graph Completion for Artwork Explanation
%A Zhou, Xuan
%A Wei, Xuefeng
%A Kato, Yuta
%A Ozaki, Shintaro
%A Hayashi, Kazuki
%A Sakai, Yusuke
%A Kamigaito, Hidetaka
%A Hayashi, Katsuhiko
%A Watanabe, Taro
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F zhou-etal-2026-artkgc
%X Explaining an artwork requires knowledge beyond visual recognition, including facts about its creator, subject, material, style, collection, and historical context. Knowledge graphs can provide such evidence, but artwork KGs are incomplete, especially for newly encountered artworks. We introduce ArtKGC, a leakage-controlled multimodal benchmark and evaluation protocol for artwork knowledge graph completion. ArtKGC links artworks to Wikidata facts, Wikipedia descriptions, and visual evidence while controlling ambiguous mappings, graph leakage, and descriptions that directly reveal held-out answers. We show that graph-only models are weak for unseen artworks, raw text can inflate evaluation through answer leakage, and visual evidence is strongly relation-dependent. As an interpretable diagnostic baseline, we use a validation-calibrated reranker that combines structural, sentence-redacted textual, and visual evidence. Experiments show improved completion in the primary inductive-artwork setting and modest downstream evidence gains for artwork QA and explanation diagnostics.
%U https://aclanthology.org/2026.findings-emnlp.2299/
%P 49291-49309
Markdown (Informal)
[ARTKGC: Leakage-Controlled Multimodal Knowledge Graph Completion for Artwork Explanation](https://aclanthology.org/2026.findings-emnlp.2299/) (Zhou et al., Findings 2026)
ACL
- Xuan Zhou, Xuefeng Wei, Yuta Kato, Shintaro Ozaki, Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, and Taro Watanabe. 2026. ARTKGC: Leakage-Controlled Multimodal Knowledge Graph Completion for Artwork Explanation. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 49291–49309, Budapest, Hungary. Association for Computational Linguistics.