@inproceedings{maurya-etal-2026-colorism,
title = "Colorism in Multimodal {AI}: An Empirical Exploration of Socioeconomic Linguistic Bias in Text-to-Image Generation",
author = "Maurya, Raj Gaurav and
Shukla, Vaibhav and
Panat, Sreedath",
editor = "Baez Santamaria, Selene and
Somayajula, Sai Ashish and
Yamaguchi, Atsuki",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 4: Student Research Workshop)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-srw.69/",
pages = "937--951",
ISBN = "979-8-89176-383-8",
abstract = "The recent rapid real-world adoption of vision-language models (VLMs) raises concerns about how social biases encoded in language may propagate into visual generation. In this work, we examine whether socioeconomic stereotypes, expressed through occupation and income-related linguistic cues in prompts, systematically influences skin-tone representations in text-to-image (T2I) generation, with a focus on colorism as a visual marker of social inequality. We first benchmark 3 small VLMs and 60 human annotators on the Monk Skin Tone (MST) scale using the MST-E dataset. We then conduct a large-scale T2I generation study in which we systematically vary the linguistic framing of income in prompts describing 210 occupations, producing over 2,500 portraits across 3 large VLMs. The skin-tone audit of the portraits by the best-performing annotator (GPT-5 mini) reveals strong color bias: high-income prompts consistently produce lighter-skinned faces, with prompt constraints only modestly attenuating this effect. Bias magnitude varies across generators, with GPT-5 Image-mini and Gemini-2.5 Flash-Image exhibiting more pronounced shifts in MST than Grok-2 Image. Our findings indicate that VLMs encode and amplify ethnoracialized socioeconomic stereotypes in language-conditioned image generation, underscoring the need for cross-modal fairness audits and human-centered evaluations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maurya-etal-2026-colorism">
<titleInfo>
<title>Colorism in Multimodal AI: An Empirical Exploration of Socioeconomic Linguistic Bias in Text-to-Image Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="given">Gaurav</namePart>
<namePart type="family">Maurya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vaibhav</namePart>
<namePart type="family">Shukla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sreedath</namePart>
<namePart type="family">Panat</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 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Selene</namePart>
<namePart type="family">Baez Santamaria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Ashish</namePart>
<namePart type="family">Somayajula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsuki</namePart>
<namePart type="family">Yamaguchi</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">979-8-89176-383-8</identifier>
</relatedItem>
<abstract>The recent rapid real-world adoption of vision-language models (VLMs) raises concerns about how social biases encoded in language may propagate into visual generation. In this work, we examine whether socioeconomic stereotypes, expressed through occupation and income-related linguistic cues in prompts, systematically influences skin-tone representations in text-to-image (T2I) generation, with a focus on colorism as a visual marker of social inequality. We first benchmark 3 small VLMs and 60 human annotators on the Monk Skin Tone (MST) scale using the MST-E dataset. We then conduct a large-scale T2I generation study in which we systematically vary the linguistic framing of income in prompts describing 210 occupations, producing over 2,500 portraits across 3 large VLMs. The skin-tone audit of the portraits by the best-performing annotator (GPT-5 mini) reveals strong color bias: high-income prompts consistently produce lighter-skinned faces, with prompt constraints only modestly attenuating this effect. Bias magnitude varies across generators, with GPT-5 Image-mini and Gemini-2.5 Flash-Image exhibiting more pronounced shifts in MST than Grok-2 Image. Our findings indicate that VLMs encode and amplify ethnoracialized socioeconomic stereotypes in language-conditioned image generation, underscoring the need for cross-modal fairness audits and human-centered evaluations.</abstract>
<identifier type="citekey">maurya-etal-2026-colorism</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-srw.69/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>937</start>
<end>951</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Colorism in Multimodal AI: An Empirical Exploration of Socioeconomic Linguistic Bias in Text-to-Image Generation
%A Maurya, Raj Gaurav
%A Shukla, Vaibhav
%A Panat, Sreedath
%Y Baez Santamaria, Selene
%Y Somayajula, Sai Ashish
%Y Yamaguchi, Atsuki
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-383-8
%F maurya-etal-2026-colorism
%X The recent rapid real-world adoption of vision-language models (VLMs) raises concerns about how social biases encoded in language may propagate into visual generation. In this work, we examine whether socioeconomic stereotypes, expressed through occupation and income-related linguistic cues in prompts, systematically influences skin-tone representations in text-to-image (T2I) generation, with a focus on colorism as a visual marker of social inequality. We first benchmark 3 small VLMs and 60 human annotators on the Monk Skin Tone (MST) scale using the MST-E dataset. We then conduct a large-scale T2I generation study in which we systematically vary the linguistic framing of income in prompts describing 210 occupations, producing over 2,500 portraits across 3 large VLMs. The skin-tone audit of the portraits by the best-performing annotator (GPT-5 mini) reveals strong color bias: high-income prompts consistently produce lighter-skinned faces, with prompt constraints only modestly attenuating this effect. Bias magnitude varies across generators, with GPT-5 Image-mini and Gemini-2.5 Flash-Image exhibiting more pronounced shifts in MST than Grok-2 Image. Our findings indicate that VLMs encode and amplify ethnoracialized socioeconomic stereotypes in language-conditioned image generation, underscoring the need for cross-modal fairness audits and human-centered evaluations.
%U https://aclanthology.org/2026.eacl-srw.69/
%P 937-951
Markdown (Informal)
[Colorism in Multimodal AI: An Empirical Exploration of Socioeconomic Linguistic Bias in Text-to-Image Generation](https://aclanthology.org/2026.eacl-srw.69/) (Maurya et al., EACL 2026)
ACL