@inproceedings{kamruzzaman-etal-2025-seeing,
title = "Seeing Race, Feeling Bias: Emotion Stereotyping in Multimodal Language Models",
author = "Kamruzzaman, Mahammed and
Curry, Amanda Cercas and
Cercas Curry, Alba and
Plaza-del-Arco, Flor Miriam",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.386/",
doi = "10.18653/v1/2025.findings-emnlp.386",
pages = "7317--7351",
ISBN = "979-8-89176-335-7",
abstract = "Large language models (LLMs) are increasingly used to predict human emotions, but previous studies show that these models reproduce gendered emotion stereotypes. Emotion stereotypes are also tightly tied to race and skin tone (consider for example the trope of the angry black woman), but previous work has thus far overlooked this dimension. In this paper, we address this gap by introducing the first large-scale multimodal study of racial, gender, and skin-tone bias in emotion attribution, revealing how modality (text, images) and their combination shape emotion stereotypes in Multimodal LLMs (MLLMs). We evaluate four open-source MLLMs using 2.1K emotion-related events paired with 400 neutral face images across three different prompt strategies. Our findings reveal varying biases in MLLMs representations of different racial groups: models reproduce racial stereotypes across modalities, with textual cues being particularly noticeable. Models also reproduce colourist trends, with darker skin tones showing more skew. Our research highlights the need for future rigorous evaluation and mitigation strategies that account for race, colorism, and gender in MLLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kamruzzaman-etal-2025-seeing">
<titleInfo>
<title>Seeing Race, Feeling Bias: Emotion Stereotyping in Multimodal Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahammed</namePart>
<namePart type="family">Kamruzzaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="given">Cercas</namePart>
<namePart type="family">Curry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alba</namePart>
<namePart type="family">Cercas Curry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flor</namePart>
<namePart type="given">Miriam</namePart>
<namePart type="family">Plaza-del-Arco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</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">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are increasingly used to predict human emotions, but previous studies show that these models reproduce gendered emotion stereotypes. Emotion stereotypes are also tightly tied to race and skin tone (consider for example the trope of the angry black woman), but previous work has thus far overlooked this dimension. In this paper, we address this gap by introducing the first large-scale multimodal study of racial, gender, and skin-tone bias in emotion attribution, revealing how modality (text, images) and their combination shape emotion stereotypes in Multimodal LLMs (MLLMs). We evaluate four open-source MLLMs using 2.1K emotion-related events paired with 400 neutral face images across three different prompt strategies. Our findings reveal varying biases in MLLMs representations of different racial groups: models reproduce racial stereotypes across modalities, with textual cues being particularly noticeable. Models also reproduce colourist trends, with darker skin tones showing more skew. Our research highlights the need for future rigorous evaluation and mitigation strategies that account for race, colorism, and gender in MLLMs.</abstract>
<identifier type="citekey">kamruzzaman-etal-2025-seeing</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.386</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.386/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>7317</start>
<end>7351</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Seeing Race, Feeling Bias: Emotion Stereotyping in Multimodal Language Models
%A Kamruzzaman, Mahammed
%A Curry, Amanda Cercas
%A Cercas Curry, Alba
%A Plaza-del-Arco, Flor Miriam
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F kamruzzaman-etal-2025-seeing
%X Large language models (LLMs) are increasingly used to predict human emotions, but previous studies show that these models reproduce gendered emotion stereotypes. Emotion stereotypes are also tightly tied to race and skin tone (consider for example the trope of the angry black woman), but previous work has thus far overlooked this dimension. In this paper, we address this gap by introducing the first large-scale multimodal study of racial, gender, and skin-tone bias in emotion attribution, revealing how modality (text, images) and their combination shape emotion stereotypes in Multimodal LLMs (MLLMs). We evaluate four open-source MLLMs using 2.1K emotion-related events paired with 400 neutral face images across three different prompt strategies. Our findings reveal varying biases in MLLMs representations of different racial groups: models reproduce racial stereotypes across modalities, with textual cues being particularly noticeable. Models also reproduce colourist trends, with darker skin tones showing more skew. Our research highlights the need for future rigorous evaluation and mitigation strategies that account for race, colorism, and gender in MLLMs.
%R 10.18653/v1/2025.findings-emnlp.386
%U https://aclanthology.org/2025.findings-emnlp.386/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.386
%P 7317-7351
Markdown (Informal)
[Seeing Race, Feeling Bias: Emotion Stereotyping in Multimodal Language Models](https://aclanthology.org/2025.findings-emnlp.386/) (Kamruzzaman et al., Findings 2025)
ACL