<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khurana-etal-2025-defverify">
    <titleInfo>
        <title>DefVerify: Do Hate Speech Models Reflect Their Dataset‘s Definition?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Urja</namePart>
        <namePart type="family">Khurana</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eric</namePart>
        <namePart type="family">Nalisnick</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Antske</namePart>
        <namePart type="family">Fokkens</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-01</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 31st International Conference on Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Owen</namePart>
            <namePart type="family">Rambow</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Leo</namePart>
            <namePart type="family">Wanner</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marianna</namePart>
            <namePart type="family">Apidianaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hend</namePart>
            <namePart type="family">Al-Khalifa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Barbara</namePart>
            <namePart type="given">Di</namePart>
            <namePart type="family">Eugenio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Steven</namePart>
            <namePart type="family">Schockaert</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, UAE</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>When building a predictive model, it is often difficult to ensure that application-specific requirements are encoded by the model that will eventually be deployed. Consider researchers working on hate speech detection. They will have an idea of what is considered hate speech, but building a model that reflects their view accurately requires preserving those ideals throughout the workflow of data set construction and model training. Complications such as sampling bias, annotation bias, and model misspecification almost always arise, possibly resulting in a gap between the application specification and the model‘s actual behavior upon deployment. To address this issue for hate speech detection, we propose DefVerify: a 3-step procedure that (i) encodes a user-specified definition of hate speech, (ii) quantifies to what extent the model reflects the intended definition, and (iii) tries to identify the point of failure in the workflow. We use DefVerify to find gaps between definition and model behavior when applied to six popular hate speech benchmark datasets.</abstract>
    <identifier type="citekey">khurana-etal-2025-defverify</identifier>
    <location>
        <url>https://aclanthology.org/2025.coling-main.293/</url>
    </location>
    <part>
        <date>2025-01</date>
        <extent unit="page">
            <start>4341</start>
            <end>4358</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DefVerify: Do Hate Speech Models Reflect Their Dataset‘s Definition?
%A Khurana, Urja
%A Nalisnick, Eric
%A Fokkens, Antske
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F khurana-etal-2025-defverify
%X When building a predictive model, it is often difficult to ensure that application-specific requirements are encoded by the model that will eventually be deployed. Consider researchers working on hate speech detection. They will have an idea of what is considered hate speech, but building a model that reflects their view accurately requires preserving those ideals throughout the workflow of data set construction and model training. Complications such as sampling bias, annotation bias, and model misspecification almost always arise, possibly resulting in a gap between the application specification and the model‘s actual behavior upon deployment. To address this issue for hate speech detection, we propose DefVerify: a 3-step procedure that (i) encodes a user-specified definition of hate speech, (ii) quantifies to what extent the model reflects the intended definition, and (iii) tries to identify the point of failure in the workflow. We use DefVerify to find gaps between definition and model behavior when applied to six popular hate speech benchmark datasets.
%U https://aclanthology.org/2025.coling-main.293/
%P 4341-4358

Markdown (Informal)

[DefVerify: Do Hate Speech Models Reflect Their Dataset’s Definition?](https://aclanthology.org/2025.coling-main.293/) (Khurana et al., COLING 2025)

• DefVerify: Do Hate Speech Models Reflect Their Dataset’s Definition? (Khurana et al., COLING 2025)

ACL

• Urja Khurana, Eric Nalisnick, and Antske Fokkens. 2025. DefVerify: Do Hate Speech Models Reflect Their Dataset’s Definition?. In Proceedings of the 31st International Conference on Computational Linguistics, pages 4341–4358, Abu Dhabi, UAE. Association for Computational Linguistics.