<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghosh-caliskan-2023-person">
    <titleInfo>
        <title>‘Person’ == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sourojit</namePart>
        <namePart type="family">Ghosh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aylin</namePart>
        <namePart type="family">Caliskan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We study stereotypes embedded within one of the most popular text-to-image generators: Stable Diffusion. We answer the question: what stereotypes of gender and nationality/continental identity does Stable Diffusion display in the absence of such information i.e. what gender and nationality/continental identity is assigned to ‘a person,’ or to ‘a person from Asia.’ Using CLIP-cosine similarity for zero-shot classification of images generated by CLIP-based Stable Diffusion v2.1 verified by manual examination, we chronicle results from 136 prompts (50 results/prompt) of front-facing images of faces from 6 different continents, 27 countries and 3 genders. We observe how Stable Diffusion results of ‘a person’ without any additional gender/nationality information correspond closest to images of men (avg. similarity 0.64) and least with persons of nonbinary gender (avg. similarity 0.41), and to persons from Europe/North America (avg. similarities 0.71 and 0.68, respectively) over Africa/Asia (avg. similarities 0.43 and 0.41, respectively), pointing towards Stable Diffusion having a concerning representation of personhood to be a European/North American man. We also show continental stereotypes and resultant harms e.g. a person from Oceania is deemed to be Australian/New Zealander (avg. similarities 0.77 and 0.74, respectively) over Papua New Guinean (avg. similarity 0.31), pointing to the erasure of Indigenous Oceanic peoples, who form a majority over descendants of colonizers both in Papua New Guinea and in Oceania overall. Finally, we unexpectedly observe a pattern of sexualization of women, specifically Latin American, Mexican, Indian and Egyptian women, confirmed through an NSFW detector and verified by manual examination. This demonstrates how Stable Diffusion perpetuates Western fetishization of women of color through objectification in media, which if left unchecked will worsen this stereotypical representation. All code and relevant data will be made publicly available.</abstract>
    <identifier type="citekey">ghosh-caliskan-2023-person</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.465</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.465</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>6971</start>
            <end>6985</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ‘Person’ == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion
%A Ghosh, Sourojit
%A Caliskan, Aylin
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F ghosh-caliskan-2023-person
%X We study stereotypes embedded within one of the most popular text-to-image generators: Stable Diffusion. We answer the question: what stereotypes of gender and nationality/continental identity does Stable Diffusion display in the absence of such information i.e. what gender and nationality/continental identity is assigned to ‘a person,’ or to ‘a person from Asia.’ Using CLIP-cosine similarity for zero-shot classification of images generated by CLIP-based Stable Diffusion v2.1 verified by manual examination, we chronicle results from 136 prompts (50 results/prompt) of front-facing images of faces from 6 different continents, 27 countries and 3 genders. We observe how Stable Diffusion results of ‘a person’ without any additional gender/nationality information correspond closest to images of men (avg. similarity 0.64) and least with persons of nonbinary gender (avg. similarity 0.41), and to persons from Europe/North America (avg. similarities 0.71 and 0.68, respectively) over Africa/Asia (avg. similarities 0.43 and 0.41, respectively), pointing towards Stable Diffusion having a concerning representation of personhood to be a European/North American man. We also show continental stereotypes and resultant harms e.g. a person from Oceania is deemed to be Australian/New Zealander (avg. similarities 0.77 and 0.74, respectively) over Papua New Guinean (avg. similarity 0.31), pointing to the erasure of Indigenous Oceanic peoples, who form a majority over descendants of colonizers both in Papua New Guinea and in Oceania overall. Finally, we unexpectedly observe a pattern of sexualization of women, specifically Latin American, Mexican, Indian and Egyptian women, confirmed through an NSFW detector and verified by manual examination. This demonstrates how Stable Diffusion perpetuates Western fetishization of women of color through objectification in media, which if left unchecked will worsen this stereotypical representation. All code and relevant data will be made publicly available.
%R 10.18653/v1/2023.findings-emnlp.465
%U https://aclanthology.org/2023.findings-emnlp.465
%U https://doi.org/10.18653/v1/2023.findings-emnlp.465
%P 6971-6985

Markdown (Informal)

[‘Person’ == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion](https://aclanthology.org/2023.findings-emnlp.465) (Ghosh & Caliskan, Findings 2023)

• ‘Person’ == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion (Ghosh & Caliskan, Findings 2023)

ACL

• Sourojit Ghosh and Aylin Caliskan. 2023. ‘Person’ == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 6971–6985, Singapore. Association for Computational Linguistics.