@inproceedings{kadiyala-etal-2025-uncovering,
title = "Uncovering Cultural Representation Disparities in Vision-Language Models",
author = "Kadiyala, Ram Mohan Rao and
Gupta, Siddhant and
Purbey, Jebish and
Yadav, Srishti and
Debnath, Suman and
Salamanca, Alejandro R. and
Elliott, Desmond",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-ijcnlp.131/",
pages = "2087--2117",
ISBN = "979-8-89176-303-6",
abstract = "Vision-Language Models (VLMs) have demonstrated impressive capabilities across a range of tasks, yet concerns about their potential biases persist. This work investigates the cultural biases in state-of-the-art VLMs by evaluating their performance on an image-based country identification task at the country level. Utilizing the geographically diverse Country211 (CITATION) dataset, we probe VLMs via open-ended questions, multiple-choice questions (MCQs), and include challenging multilingual and adversarial task settings. Our analysis aims to uncover disparities in model accuracy across different countries and question formats, providing insights into how training data distribution and evaluation methodologies may influence cultural biases in VLMs. The findings highlight significant variations in performance, suggesting that while VLMs possess considerable visual understanding, they inherit biases from their pre-training data and scale, which impact their ability to generalize uniformly across diverse global contexts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kadiyala-etal-2025-uncovering">
<titleInfo>
<title>Uncovering Cultural Representation Disparities in Vision-Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ram</namePart>
<namePart type="given">Mohan</namePart>
<namePart type="given">Rao</namePart>
<namePart type="family">Kadiyala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddhant</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jebish</namePart>
<namePart type="family">Purbey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srishti</namePart>
<namePart type="family">Yadav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suman</namePart>
<namePart type="family">Debnath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alejandro</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Salamanca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<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">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-303-6</identifier>
</relatedItem>
<abstract>Vision-Language Models (VLMs) have demonstrated impressive capabilities across a range of tasks, yet concerns about their potential biases persist. This work investigates the cultural biases in state-of-the-art VLMs by evaluating their performance on an image-based country identification task at the country level. Utilizing the geographically diverse Country211 (CITATION) dataset, we probe VLMs via open-ended questions, multiple-choice questions (MCQs), and include challenging multilingual and adversarial task settings. Our analysis aims to uncover disparities in model accuracy across different countries and question formats, providing insights into how training data distribution and evaluation methodologies may influence cultural biases in VLMs. The findings highlight significant variations in performance, suggesting that while VLMs possess considerable visual understanding, they inherit biases from their pre-training data and scale, which impact their ability to generalize uniformly across diverse global contexts.</abstract>
<identifier type="citekey">kadiyala-etal-2025-uncovering</identifier>
<location>
<url>https://aclanthology.org/2025.findings-ijcnlp.131/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>2087</start>
<end>2117</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Uncovering Cultural Representation Disparities in Vision-Language Models
%A Kadiyala, Ram Mohan Rao
%A Gupta, Siddhant
%A Purbey, Jebish
%A Yadav, Srishti
%A Debnath, Suman
%A Salamanca, Alejandro R.
%A Elliott, Desmond
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-303-6
%F kadiyala-etal-2025-uncovering
%X Vision-Language Models (VLMs) have demonstrated impressive capabilities across a range of tasks, yet concerns about their potential biases persist. This work investigates the cultural biases in state-of-the-art VLMs by evaluating their performance on an image-based country identification task at the country level. Utilizing the geographically diverse Country211 (CITATION) dataset, we probe VLMs via open-ended questions, multiple-choice questions (MCQs), and include challenging multilingual and adversarial task settings. Our analysis aims to uncover disparities in model accuracy across different countries and question formats, providing insights into how training data distribution and evaluation methodologies may influence cultural biases in VLMs. The findings highlight significant variations in performance, suggesting that while VLMs possess considerable visual understanding, they inherit biases from their pre-training data and scale, which impact their ability to generalize uniformly across diverse global contexts.
%U https://aclanthology.org/2025.findings-ijcnlp.131/
%P 2087-2117
Markdown (Informal)
[Uncovering Cultural Representation Disparities in Vision-Language Models](https://aclanthology.org/2025.findings-ijcnlp.131/) (Kadiyala et al., Findings 2025)
ACL
- Ram Mohan Rao Kadiyala, Siddhant Gupta, Jebish Purbey, Srishti Yadav, Suman Debnath, Alejandro R. Salamanca, and Desmond Elliott. 2025. Uncovering Cultural Representation Disparities in Vision-Language Models. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 2087–2117, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.