@inproceedings{zhang-etal-2026-multimodal,
title = "Multimodal {B}oolean Logic Culture Retrieval",
author = "Zhang, Jian and
Hu, Shuheng and
Chang, Jiutian and
Guo, Junyi and
Lu, Huanda and
Wang, Qiufeng and
Wu, Fangyu",
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.1747/",
doi = "10.18653/2026.findings-emnlp.1747",
pages = "37380--37389",
ISBN = "979-8-89176-462-0",
abstract = "Cultural image retrieval is essential for organizing and analyzing large-scale digital heritage resources. However, existing multimodal retrieval methods usually encode a query as a holistic embedding, making it difficult to preserve logical operators and cultural relations during retrieval. Therefore, we introduce Multimodal Boolean Logic Culture Retrieval, a novel task that moves beyond general visual similarity by enforcing strict Boolean constraints over structured cultural elements. To tackle this, we propose *CLAIR*, a training-free framework that reformulates the retrieval objective to seamlessly integrate logical operations directly within the multimodal embedding space. Furthermore, we construct CulTi2.0, a dedicated benchmark designed to evaluate diverse logical query forms based on cultural visual atoms. Extensive experiments show that while current multimodal models struggle with explicit logical queries, *CLAIR* provides consistent and generalizable improvements as a plug-and-play solution across various datasets and model families. Code and dataset are publicly available at https://github.com/AI4Culture/CulTi2.0."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-multimodal">
<titleInfo>
<title>Multimodal Boolean Logic Culture Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuheng</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiutian</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huanda</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiufeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fangyu</namePart>
<namePart type="family">Wu</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>Cultural image retrieval is essential for organizing and analyzing large-scale digital heritage resources. However, existing multimodal retrieval methods usually encode a query as a holistic embedding, making it difficult to preserve logical operators and cultural relations during retrieval. Therefore, we introduce Multimodal Boolean Logic Culture Retrieval, a novel task that moves beyond general visual similarity by enforcing strict Boolean constraints over structured cultural elements. To tackle this, we propose *CLAIR*, a training-free framework that reformulates the retrieval objective to seamlessly integrate logical operations directly within the multimodal embedding space. Furthermore, we construct CulTi2.0, a dedicated benchmark designed to evaluate diverse logical query forms based on cultural visual atoms. Extensive experiments show that while current multimodal models struggle with explicit logical queries, *CLAIR* provides consistent and generalizable improvements as a plug-and-play solution across various datasets and model families. Code and dataset are publicly available at https://github.com/AI4Culture/CulTi2.0.</abstract>
<identifier type="citekey">zhang-etal-2026-multimodal</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.1747</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1747/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>37380</start>
<end>37389</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal Boolean Logic Culture Retrieval
%A Zhang, Jian
%A Hu, Shuheng
%A Chang, Jiutian
%A Guo, Junyi
%A Lu, Huanda
%A Wang, Qiufeng
%A Wu, Fangyu
%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 zhang-etal-2026-multimodal
%X Cultural image retrieval is essential for organizing and analyzing large-scale digital heritage resources. However, existing multimodal retrieval methods usually encode a query as a holistic embedding, making it difficult to preserve logical operators and cultural relations during retrieval. Therefore, we introduce Multimodal Boolean Logic Culture Retrieval, a novel task that moves beyond general visual similarity by enforcing strict Boolean constraints over structured cultural elements. To tackle this, we propose *CLAIR*, a training-free framework that reformulates the retrieval objective to seamlessly integrate logical operations directly within the multimodal embedding space. Furthermore, we construct CulTi2.0, a dedicated benchmark designed to evaluate diverse logical query forms based on cultural visual atoms. Extensive experiments show that while current multimodal models struggle with explicit logical queries, *CLAIR* provides consistent and generalizable improvements as a plug-and-play solution across various datasets and model families. Code and dataset are publicly available at https://github.com/AI4Culture/CulTi2.0.
%R 10.18653/2026.findings-emnlp.1747
%U https://aclanthology.org/2026.findings-emnlp.1747/
%U https://doi.org/10.18653/2026.findings-emnlp.1747
%P 37380-37389
Markdown (Informal)
[Multimodal Boolean Logic Culture Retrieval](https://aclanthology.org/2026.findings-emnlp.1747/) (Zhang et al., Findings 2026)
ACL
- Jian Zhang, Shuheng Hu, Jiutian Chang, Junyi Guo, Huanda Lu, Qiufeng Wang, and Fangyu Wu. 2026. Multimodal Boolean Logic Culture Retrieval. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 37380–37389, Budapest, Hungary. Association for Computational Linguistics.