<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="raj-etal-2024-biasdora">
    <titleInfo>
        <title>BiasDora: Exploring Hidden Biased Associations in Vision-Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chahat</namePart>
        <namePart type="family">Raj</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anjishnu</namePart>
        <namePart type="family">Mukherjee</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>
    <name type="personal">
        <namePart type="given">Antonios</namePart>
        <namePart type="family">Anastasopoulos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ziwei</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Existing works examining Vision-Language Models (VLMs) for social biases predominantly focus on a limited set of documented bias associations, such as gender-profession or race-crime. This narrow scope often overlooks a vast range of unexamined implicit associations, restricting the identification and, hence, mitigation of such biases. We address this gap by probing VLMs to (1) uncover hidden, implicit associations across 9 bias dimensions. We systematically explore diverse input and output modalities and (2) demonstrate how biased associations vary in their negativity, toxicity, and extremity. Our work (3) identifies subtle and extreme biases that are typically not recognized by existing methodologies. We make the **D**ataset **o**f **r**etrieved **a**ssociations (**Dora**) publicly available.</abstract>
    <identifier type="citekey">raj-etal-2024-biasdora</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-emnlp.611</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>10439</start>
            <end>10455</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T BiasDora: Exploring Hidden Biased Associations in Vision-Language Models
%A Raj, Chahat
%A Mukherjee, Anjishnu
%A Caliskan, Aylin
%A Anastasopoulos, Antonios
%A Zhu, Ziwei
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F raj-etal-2024-biasdora
%X Existing works examining Vision-Language Models (VLMs) for social biases predominantly focus on a limited set of documented bias associations, such as gender-profession or race-crime. This narrow scope often overlooks a vast range of unexamined implicit associations, restricting the identification and, hence, mitigation of such biases. We address this gap by probing VLMs to (1) uncover hidden, implicit associations across 9 bias dimensions. We systematically explore diverse input and output modalities and (2) demonstrate how biased associations vary in their negativity, toxicity, and extremity. Our work (3) identifies subtle and extreme biases that are typically not recognized by existing methodologies. We make the **D**ataset **o**f **r**etrieved **a**ssociations (**Dora**) publicly available.
%U https://aclanthology.org/2024.findings-emnlp.611
%P 10439-10455

Markdown (Informal)

[BiasDora: Exploring Hidden Biased Associations in Vision-Language Models](https://aclanthology.org/2024.findings-emnlp.611) (Raj et al., Findings 2024)

• BiasDora: Exploring Hidden Biased Associations in Vision-Language Models (Raj et al., Findings 2024)

ACL

• Chahat Raj, Anjishnu Mukherjee, Aylin Caliskan, Antonios Anastasopoulos, and Ziwei Zhu. 2024. BiasDora: Exploring Hidden Biased Associations in Vision-Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 10439–10455, Miami, Florida, USA. Association for Computational Linguistics.