<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="iskander-etal-2024-leveraging">
    <titleInfo>
        <title>Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shadi</namePart>
        <namePart type="family">Iskander</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kira</namePart>
        <namePart type="family">Radinsky</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yonatan</namePart>
        <namePart type="family">Belinkov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kevin</namePart>
            <namePart type="family">Duh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Helena</namePart>
            <namePart type="family">Gomez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Steven</namePart>
            <namePart type="family">Bethard</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mexico City, Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Mitigating social biases typically requires identifying the social groups associated with each data sample. In this paper, we present DAFair, a novel approach to address social bias in language models. Unlike traditional methods that rely on explicit demographic labels, our approach does not require any such information. Instead, we leverage predefined prototypical demographic texts and incorporate a regularization term during the fine-tuning process to mitigate bias in the model’s representations. Our empirical results across two tasks and two models demonstrate the effectiveness of our method compared to previous approaches that do not rely on labeled data. Moreover, with limited demographic-annotated data, our approach outperforms common debiasing approaches.</abstract>
    <identifier type="citekey">iskander-etal-2024-leveraging</identifier>
    <identifier type="doi">10.18653/v1/2024.naacl-short.33</identifier>
    <location>
        <url>https://aclanthology.org/2024.naacl-short.33</url>
    </location>
    <part>
        <date>2024-06</date>
        <extent unit="page">
            <start>379</start>
            <end>390</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information
%A Iskander, Shadi
%A Radinsky, Kira
%A Belinkov, Yonatan
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F iskander-etal-2024-leveraging
%X Mitigating social biases typically requires identifying the social groups associated with each data sample. In this paper, we present DAFair, a novel approach to address social bias in language models. Unlike traditional methods that rely on explicit demographic labels, our approach does not require any such information. Instead, we leverage predefined prototypical demographic texts and incorporate a regularization term during the fine-tuning process to mitigate bias in the model’s representations. Our empirical results across two tasks and two models demonstrate the effectiveness of our method compared to previous approaches that do not rely on labeled data. Moreover, with limited demographic-annotated data, our approach outperforms common debiasing approaches.
%R 10.18653/v1/2024.naacl-short.33
%U https://aclanthology.org/2024.naacl-short.33
%U https://doi.org/10.18653/v1/2024.naacl-short.33
%P 379-390

Markdown (Informal)

[Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information](https://aclanthology.org/2024.naacl-short.33) (Iskander et al., NAACL 2024)

• Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information (Iskander et al., NAACL 2024)

ACL

• Shadi Iskander, Kira Radinsky, and Yonatan Belinkov. 2024. Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages 379–390, Mexico City, Mexico. Association for Computational Linguistics.