<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pan-etal-2026-mans">
    <titleInfo>
        <title>A Man’s World: Measuring Gender Bias in Occupational Status Judgments with Vision-Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ronghao</namePart>
        <namePart type="family">Pan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tomas</namePart>
        <namePart type="family">Bernal-Beltran</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">José</namePart>
        <namePart type="given">Antonio</namePart>
        <namePart type="family">García-Díaz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rafael</namePart>
        <namePart type="family">Valencia-García</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Vision-language models can be used in applications that analyze people in professional and social contexts. This raises concerns about whether these models reproduce occupational gender stereotypes. However, it is challenging to evaluate these associations because naturally collected images often combine demographic attributes with clothing, pose, background, and other status-related cues. We introduce a paired-image benchmark to study occupational status judgments in VLMs, containing 5,487 human-validated synthetic images spanning 41 ISCO-08 sub-major occupational groups aggregated into 10 major groups, 7 ethnicity categories, and 5 age groups. Men and women are matched based on occupation, age, ethnicity, and workplace context. We evaluate 5 VLMs using spatial comparisons that avoid direct gender references, explicit gender comparisons, and structured reasoning prompts. We observe persistent male-oriented associations in earnings judgments, even when the prompts avoid direct references to gender. Furthermore, we find that men are more frequently associated with authority, seniority, and earning potential, whereas women are more often associated with warmth. Promotion likelihood exhibits a model-family-dependent pattern: male-oriented associations emerge across Qwen-3-VL models, whereas both Gemma-3 models show the opposite, female-oriented pattern. These findings show that occupational gender stereotypes persist in the evaluated VLMs even under tightly controlled visual conditions. Our code and data are publicly available at https://github.com/NLP-UMUTeam/OccuBiasBench</abstract>
    <identifier type="citekey">pan-etal-2026-mans</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.376/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>7936</start>
            <end>7965</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Man’s World: Measuring Gender Bias in Occupational Status Judgments with Vision-Language Models
%A Pan, Ronghao
%A Bernal-Beltran, Tomas
%A García-Díaz, José Antonio
%A Valencia-García, Rafael
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F pan-etal-2026-mans
%X Vision-language models can be used in applications that analyze people in professional and social contexts. This raises concerns about whether these models reproduce occupational gender stereotypes. However, it is challenging to evaluate these associations because naturally collected images often combine demographic attributes with clothing, pose, background, and other status-related cues. We introduce a paired-image benchmark to study occupational status judgments in VLMs, containing 5,487 human-validated synthetic images spanning 41 ISCO-08 sub-major occupational groups aggregated into 10 major groups, 7 ethnicity categories, and 5 age groups. Men and women are matched based on occupation, age, ethnicity, and workplace context. We evaluate 5 VLMs using spatial comparisons that avoid direct gender references, explicit gender comparisons, and structured reasoning prompts. We observe persistent male-oriented associations in earnings judgments, even when the prompts avoid direct references to gender. Furthermore, we find that men are more frequently associated with authority, seniority, and earning potential, whereas women are more often associated with warmth. Promotion likelihood exhibits a model-family-dependent pattern: male-oriented associations emerge across Qwen-3-VL models, whereas both Gemma-3 models show the opposite, female-oriented pattern. These findings show that occupational gender stereotypes persist in the evaluated VLMs even under tightly controlled visual conditions. Our code and data are publicly available at https://github.com/NLP-UMUTeam/OccuBiasBench
%U https://aclanthology.org/2026.findings-emnlp.376/
%P 7936-7965

Markdown (Informal)

[A Man’s World: Measuring Gender Bias in Occupational Status Judgments with Vision-Language Models](https://aclanthology.org/2026.findings-emnlp.376/) (Pan et al., Findings 2026)

• A Man’s World: Measuring Gender Bias in Occupational Status Judgments with Vision-Language Models (Pan et al., Findings 2026)

ACL

• Ronghao Pan, Tomas Bernal-Beltran, José Antonio García-Díaz, and Rafael Valencia-García. 2026. A Man’s World: Measuring Gender Bias in Occupational Status Judgments with Vision-Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 7936–7965, Budapest, Hungary. Association for Computational Linguistics.