@inproceedings{ghate-etal-2024-evaluating,
title = "Evaluating Gender Bias in Multilingual Multimodal {AI} Models: Insights from an {I}ndian Context",
author = "Ghate, Kshitish and
Choudhry, Arjun and
Bannihatti Kumar, Vanya",
editor = "Fale{\'n}ska, Agnieszka and
Basta, Christine and
Costa-juss{\`a}, Marta and
Goldfarb-Tarrant, Seraphina and
Nozza, Debora",
booktitle = "Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.gebnlp-1.21",
doi = "10.18653/v1/2024.gebnlp-1.21",
pages = "338--350",
abstract = "We evaluate gender biases in multilingual multimodal image and text models in two settings: text-to-image retrieval and text-to-image generation, to show that even seemingly gender-neutral traits generate biased results. We evaluate our framework in the context of people from India, working with two languages: English and Hindi. We work with frameworks built around mCLIP-based models to ensure a thorough evaluation of recent state-of-the-art models in the multilingual setting due to their potential for widespread applications. We analyze the results across 50 traits for retrieval and 8 traits for generation, showing that current multilingual multimodal models are biased towards men for most traits, and this problem is further exacerbated for lower-resource languages like Hindi. We further discuss potential reasons behind this observation, particularly stemming from the bias introduced by the pretraining datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghate-etal-2024-evaluating">
<titleInfo>
<title>Evaluating Gender Bias in Multilingual Multimodal AI Models: Insights from an Indian Context</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kshitish</namePart>
<namePart type="family">Ghate</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Choudhry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vanya</namePart>
<namePart type="family">Bannihatti Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agnieszka</namePart>
<namePart type="family">Faleńska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">Basta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seraphina</namePart>
<namePart type="family">Goldfarb-Tarrant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We evaluate gender biases in multilingual multimodal image and text models in two settings: text-to-image retrieval and text-to-image generation, to show that even seemingly gender-neutral traits generate biased results. We evaluate our framework in the context of people from India, working with two languages: English and Hindi. We work with frameworks built around mCLIP-based models to ensure a thorough evaluation of recent state-of-the-art models in the multilingual setting due to their potential for widespread applications. We analyze the results across 50 traits for retrieval and 8 traits for generation, showing that current multilingual multimodal models are biased towards men for most traits, and this problem is further exacerbated for lower-resource languages like Hindi. We further discuss potential reasons behind this observation, particularly stemming from the bias introduced by the pretraining datasets.</abstract>
<identifier type="citekey">ghate-etal-2024-evaluating</identifier>
<identifier type="doi">10.18653/v1/2024.gebnlp-1.21</identifier>
<location>
<url>https://aclanthology.org/2024.gebnlp-1.21</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>338</start>
<end>350</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Gender Bias in Multilingual Multimodal AI Models: Insights from an Indian Context
%A Ghate, Kshitish
%A Choudhry, Arjun
%A Bannihatti Kumar, Vanya
%Y Faleńska, Agnieszka
%Y Basta, Christine
%Y Costa-jussà, Marta
%Y Goldfarb-Tarrant, Seraphina
%Y Nozza, Debora
%S Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F ghate-etal-2024-evaluating
%X We evaluate gender biases in multilingual multimodal image and text models in two settings: text-to-image retrieval and text-to-image generation, to show that even seemingly gender-neutral traits generate biased results. We evaluate our framework in the context of people from India, working with two languages: English and Hindi. We work with frameworks built around mCLIP-based models to ensure a thorough evaluation of recent state-of-the-art models in the multilingual setting due to their potential for widespread applications. We analyze the results across 50 traits for retrieval and 8 traits for generation, showing that current multilingual multimodal models are biased towards men for most traits, and this problem is further exacerbated for lower-resource languages like Hindi. We further discuss potential reasons behind this observation, particularly stemming from the bias introduced by the pretraining datasets.
%R 10.18653/v1/2024.gebnlp-1.21
%U https://aclanthology.org/2024.gebnlp-1.21
%U https://doi.org/10.18653/v1/2024.gebnlp-1.21
%P 338-350
Markdown (Informal)
[Evaluating Gender Bias in Multilingual Multimodal AI Models: Insights from an Indian Context](https://aclanthology.org/2024.gebnlp-1.21) (Ghate et al., GeBNLP-WS 2024)
ACL