@inproceedings{yayavaram-etal-2026-caire,
title = "{CAIRE}: Cultural Attribution of Images with Retrieval",
author = "Yayavaram, Arnav and
Yayavaram, Siddharth and
Khanuja, Simran and
Saxon, Michael and
Neubig, Graham",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-long.389/",
pages = "8320--8338",
ISBN = "979-8-89176-380-7",
abstract = "As text-to-image models become increasingly prevalent, ensuring their equitable performance across diverse cultural contexts is critical. Efforts to mitigate cross-cultural biases have been hampered by trade-offs, including a loss in performance, factual inaccuracies, or offensive outputs.Despite widespread recognition of these challenges, an inability to reliably measure these biases has stalled progress. To address this gap, we introduce CAIRE (https://github.com/siddharthyayavaram/CAIRE), an evaluation metric that assesses the degree of cultural relevance of an image, given a user-defined set of labels. Our framework grounds entities and concepts in the image to a knowledge base and uses factual information to give independent graded judgments for each culture label.On a manually curated dataset of culturally salient but rare items built using language models, CAIRE surpasses all baselines by 22{\%} F1 points. Additionally, we construct two datasets for culturally universal concepts, one comprising of T2I generated outputs and another retrieved from naturally-occurring data. CAIRE achieves Pearson{'}s correlations of 0.56 and 0.66 with human ratings on these sets, based on a 5-point Likert scale of cultural relevance. This demonstrates its strong alignment with human judgment across diverse image sources."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yayavaram-etal-2026-caire">
<titleInfo>
<title>CAIRE: Cultural Attribution of Images with Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arnav</namePart>
<namePart type="family">Yayavaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Yayavaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simran</namePart>
<namePart type="family">Khanuja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Saxon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-380-7</identifier>
</relatedItem>
<abstract>As text-to-image models become increasingly prevalent, ensuring their equitable performance across diverse cultural contexts is critical. Efforts to mitigate cross-cultural biases have been hampered by trade-offs, including a loss in performance, factual inaccuracies, or offensive outputs.Despite widespread recognition of these challenges, an inability to reliably measure these biases has stalled progress. To address this gap, we introduce CAIRE (https://github.com/siddharthyayavaram/CAIRE), an evaluation metric that assesses the degree of cultural relevance of an image, given a user-defined set of labels. Our framework grounds entities and concepts in the image to a knowledge base and uses factual information to give independent graded judgments for each culture label.On a manually curated dataset of culturally salient but rare items built using language models, CAIRE surpasses all baselines by 22% F1 points. Additionally, we construct two datasets for culturally universal concepts, one comprising of T2I generated outputs and another retrieved from naturally-occurring data. CAIRE achieves Pearson’s correlations of 0.56 and 0.66 with human ratings on these sets, based on a 5-point Likert scale of cultural relevance. This demonstrates its strong alignment with human judgment across diverse image sources.</abstract>
<identifier type="citekey">yayavaram-etal-2026-caire</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-long.389/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>8320</start>
<end>8338</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CAIRE: Cultural Attribution of Images with Retrieval
%A Yayavaram, Arnav
%A Yayavaram, Siddharth
%A Khanuja, Simran
%A Saxon, Michael
%A Neubig, Graham
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F yayavaram-etal-2026-caire
%X As text-to-image models become increasingly prevalent, ensuring their equitable performance across diverse cultural contexts is critical. Efforts to mitigate cross-cultural biases have been hampered by trade-offs, including a loss in performance, factual inaccuracies, or offensive outputs.Despite widespread recognition of these challenges, an inability to reliably measure these biases has stalled progress. To address this gap, we introduce CAIRE (https://github.com/siddharthyayavaram/CAIRE), an evaluation metric that assesses the degree of cultural relevance of an image, given a user-defined set of labels. Our framework grounds entities and concepts in the image to a knowledge base and uses factual information to give independent graded judgments for each culture label.On a manually curated dataset of culturally salient but rare items built using language models, CAIRE surpasses all baselines by 22% F1 points. Additionally, we construct two datasets for culturally universal concepts, one comprising of T2I generated outputs and another retrieved from naturally-occurring data. CAIRE achieves Pearson’s correlations of 0.56 and 0.66 with human ratings on these sets, based on a 5-point Likert scale of cultural relevance. This demonstrates its strong alignment with human judgment across diverse image sources.
%U https://aclanthology.org/2026.eacl-long.389/
%P 8320-8338
Markdown (Informal)
[CAIRE: Cultural Attribution of Images with Retrieval](https://aclanthology.org/2026.eacl-long.389/) (Yayavaram et al., EACL 2026)
ACL
- Arnav Yayavaram, Siddharth Yayavaram, Simran Khanuja, Michael Saxon, and Graham Neubig. 2026. CAIRE: Cultural Attribution of Images with Retrieval. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8320–8338, Rabat, Morocco. Association for Computational Linguistics.