<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="villalba-oses-etal-2025-revealing">
    <titleInfo>
        <title>Revealing Gender Bias in Language Models through Fashion Image Captioning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Maria</namePart>
        <namePart type="family">Villalba-Oses</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Victoria</namePart>
        <namePart type="family">Muñoz-Garcia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Juan</namePart>
        <namePart type="given">Pablo</namePart>
        <namePart type="family">Consuegra-Ayala</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Galia</namePart>
            <namePart type="family">Angelova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Kunilovskaya</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marie</namePart>
            <namePart type="family">Escribe</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Image captioning bridges computer vision and natural language processing but remains vulnerable to social biases. This study evaluates gender bias in ChatGPT, Copilot, and Grok by analyzing their descriptions of fashion-related images prompted without gender cues. We introduce a methodology combining gender annotation, stereotype classification, and a manually curated dataset. Results show that GPT-4o and Grok frequently assign gender and reinforce stereotypes, while Copilot more often generates neutral captions. Grok shows the lowest error rate but consistently assigns gender, even when cues are ambiguous. These findings highlight the need for bias-aware captioning approaches in multimodal systems.</abstract>
    <identifier type="citekey">villalba-oses-etal-2025-revealing</identifier>
    <location>
        <url>https://aclanthology.org/2025.ranlp-1.155/</url>
    </location>
    <part>
        <date>2025-09</date>
        <extent unit="page">
            <start>1333</start>
            <end>1340</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Revealing Gender Bias in Language Models through Fashion Image Captioning
%A Villalba-Oses, Maria
%A Muñoz-Garcia, Victoria
%A Consuegra-Ayala, Juan Pablo
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F villalba-oses-etal-2025-revealing
%X Image captioning bridges computer vision and natural language processing but remains vulnerable to social biases. This study evaluates gender bias in ChatGPT, Copilot, and Grok by analyzing their descriptions of fashion-related images prompted without gender cues. We introduce a methodology combining gender annotation, stereotype classification, and a manually curated dataset. Results show that GPT-4o and Grok frequently assign gender and reinforce stereotypes, while Copilot more often generates neutral captions. Grok shows the lowest error rate but consistently assigns gender, even when cues are ambiguous. These findings highlight the need for bias-aware captioning approaches in multimodal systems.
%U https://aclanthology.org/2025.ranlp-1.155/
%P 1333-1340

Markdown (Informal)

[Revealing Gender Bias in Language Models through Fashion Image Captioning](https://aclanthology.org/2025.ranlp-1.155/) (Villalba-Oses et al., RANLP 2025)

• Revealing Gender Bias in Language Models through Fashion Image Captioning (Villalba-Oses et al., RANLP 2025)

ACL

• Maria Villalba-Oses, Victoria Muñoz-Garcia, and Juan Pablo Consuegra-Ayala. 2025. Revealing Gender Bias in Language Models through Fashion Image Captioning. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 1333–1340, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.