<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="parra-2024-unmasked">
    <titleInfo>
        <title>UnMASKed: Quantifying Gender Biases in Masked Language Models through Linguistically Informed Job Market Prompts</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Iñigo</namePart>
        <namePart type="family">Parra</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Neele</namePart>
            <namePart type="family">Falk</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sara</namePart>
            <namePart type="family">Papi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mike</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">St. Julian’s, Malta</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Language models (LMs) have become pivotal in the realm of technological advancements. While their capabilities are vast and transformative, they often include societal biases encoded in the human-produced datasets used for their training. This research delves into the inherent biases present in masked language models (MLMs), with a specific focus on gender biases. This study evaluated six prominent models: BERT, RoBERTa, DistilBERT, BERT- multilingual, XLM-RoBERTa, and DistilBERT- multilingual. The methodology employed a novel dataset, bifurcated into two subsets: one containing prompts that encouraged models to generate subject pronouns in English and the other requiring models to return the probabilities of verbs, adverbs, and adjectives linked to the prompts’ gender pronouns. The analysis reveals stereotypical gender alignment of all models, with multilingual variants showing comparatively reduced biases.</abstract>
    <identifier type="citekey">parra-2024-unmasked</identifier>
    <location>
        <url>https://aclanthology.org/2024.eacl-srw.6</url>
    </location>
    <part>
        <date>2024-03</date>
        <extent unit="page">
            <start>61</start>
            <end>70</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T UnMASKed: Quantifying Gender Biases in Masked Language Models through Linguistically Informed Job Market Prompts
%A Parra, Iñigo
%Y Falk, Neele
%Y Papi, Sara
%Y Zhang, Mike
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F parra-2024-unmasked
%X Language models (LMs) have become pivotal in the realm of technological advancements. While their capabilities are vast and transformative, they often include societal biases encoded in the human-produced datasets used for their training. This research delves into the inherent biases present in masked language models (MLMs), with a specific focus on gender biases. This study evaluated six prominent models: BERT, RoBERTa, DistilBERT, BERT- multilingual, XLM-RoBERTa, and DistilBERT- multilingual. The methodology employed a novel dataset, bifurcated into two subsets: one containing prompts that encouraged models to generate subject pronouns in English and the other requiring models to return the probabilities of verbs, adverbs, and adjectives linked to the prompts’ gender pronouns. The analysis reveals stereotypical gender alignment of all models, with multilingual variants showing comparatively reduced biases.
%U https://aclanthology.org/2024.eacl-srw.6
%P 61-70

Markdown (Informal)

[UnMASKed: Quantifying Gender Biases in Masked Language Models through Linguistically Informed Job Market Prompts](https://aclanthology.org/2024.eacl-srw.6) (Parra, EACL 2024)

• UnMASKed: Quantifying Gender Biases in Masked Language Models through Linguistically Informed Job Market Prompts (Parra, EACL 2024)

ACL

• Iñigo Parra. 2024. UnMASKed: Quantifying Gender Biases in Masked Language Models through Linguistically Informed Job Market Prompts. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 61–70, St. Julian’s, Malta. Association for Computational Linguistics.