Hatevolution: What Static Benchmarks Don’t Tell Us

Chiara Di Bonaventura; Barbara McGillivray; Yulan He; Albert Meroño-Peñuela

doi:10.18653/v1/2025.findings-acl.910

Hatevolution: What Static Benchmarks Don’t Tell Us

Chiara Di Bonaventura, Barbara McGillivray, Yulan He, Albert Meroño-Peñuela

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Language changes over time, including in the hate speech domain, which evolves quickly following social dynamics and cultural shifts. While NLP research has investigated the impact of language evolution on model training and has proposed several solutions for it, its impact on model benchmarking remains under-explored. Yet, hate speech benchmarks play a crucial role to ensure model safety. In this paper, we empirically evaluate the robustness of 20 language models across two evolving hate speech experiments, and we show the temporal misalignment between static and time-sensitive evaluations. Our findings call for time-sensitive linguistic benchmarks in order to correctly and reliably evaluate language models in the hate speech domain.

Anthology ID:: 2025.findings-acl.910
Volume:: Findings of the Association for Computational Linguistics: ACL 2025
Month:: July
Year:: 2025
Address:: Vienna, Austria
Editors:: Wanxiang Che, Joyce Nabende, Ekaterina Shutova, Mohammad Taher Pilehvar
Venue:: Findings
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 17695–17707
Language:
URL:: https://aclanthology.org/2025.findings-acl.910/
DOI:: 10.18653/v1/2025.findings-acl.910
Bibkey:
Cite (ACL):: Chiara Di Bonaventura, Barbara McGillivray, Yulan He, and Albert Meroño-Peñuela. 2025. Hatevolution: What Static Benchmarks Don’t Tell Us. In Findings of the Association for Computational Linguistics: ACL 2025, pages 17695–17707, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):: Hatevolution: What Static Benchmarks Don’t Tell Us (Di Bonaventura et al., Findings 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.findings-acl.910.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{di-bonaventura-etal-2025-hatevolution,
    title = "Hatevolution: What Static Benchmarks Don{'}t Tell Us",
    author = "Di Bonaventura, Chiara  and
      McGillivray, Barbara  and
      He, Yulan  and
      Mero{\~n}o-Pe{\~n}uela, Albert",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-acl.910/",
    doi = "10.18653/v1/2025.findings-acl.910",
    pages = "17695--17707",
    ISBN = "979-8-89176-256-5",
    abstract = "Language changes over time, including in the hate speech domain, which evolves quickly following social dynamics and cultural shifts. While NLP research has investigated the impact of language evolution on model training and has proposed several solutions for it, its impact on model benchmarking remains under-explored. Yet, hate speech benchmarks play a crucial role to ensure model safety. In this paper, we empirically evaluate the robustness of 20 language models across two evolving hate speech experiments, and we show the temporal misalignment between static and time-sensitive evaluations. Our findings call for time-sensitive linguistic benchmarks in order to correctly and reliably evaluate language models in the hate speech domain."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="di-bonaventura-etal-2025-hatevolution">
    <titleInfo>
        <title>Hatevolution: What Static Benchmarks Don’t Tell Us</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chiara</namePart>
        <namePart type="family">Di Bonaventura</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Barbara</namePart>
        <namePart type="family">McGillivray</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yulan</namePart>
        <namePart type="family">He</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Albert</namePart>
        <namePart type="family">Meroño-Peñuela</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>Language changes over time, including in the hate speech domain, which evolves quickly following social dynamics and cultural shifts. While NLP research has investigated the impact of language evolution on model training and has proposed several solutions for it, its impact on model benchmarking remains under-explored. Yet, hate speech benchmarks play a crucial role to ensure model safety. In this paper, we empirically evaluate the robustness of 20 language models across two evolving hate speech experiments, and we show the temporal misalignment between static and time-sensitive evaluations. Our findings call for time-sensitive linguistic benchmarks in order to correctly and reliably evaluate language models in the hate speech domain.</abstract>
    <identifier type="citekey">di-bonaventura-etal-2025-hatevolution</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.910</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.910/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>17695</start>
            <end>17707</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Hatevolution: What Static Benchmarks Don’t Tell Us
%A Di Bonaventura, Chiara
%A McGillivray, Barbara
%A He, Yulan
%A Meroño-Peñuela, Albert
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F di-bonaventura-etal-2025-hatevolution
%X Language changes over time, including in the hate speech domain, which evolves quickly following social dynamics and cultural shifts. While NLP research has investigated the impact of language evolution on model training and has proposed several solutions for it, its impact on model benchmarking remains under-explored. Yet, hate speech benchmarks play a crucial role to ensure model safety. In this paper, we empirically evaluate the robustness of 20 language models across two evolving hate speech experiments, and we show the temporal misalignment between static and time-sensitive evaluations. Our findings call for time-sensitive linguistic benchmarks in order to correctly and reliably evaluate language models in the hate speech domain.
%R 10.18653/v1/2025.findings-acl.910
%U https://aclanthology.org/2025.findings-acl.910/
%U https://doi.org/10.18653/v1/2025.findings-acl.910
%P 17695-17707

Download as File

Markdown (Informal)

[Hatevolution: What Static Benchmarks Don’t Tell Us](https://aclanthology.org/2025.findings-acl.910/) (Di Bonaventura et al., Findings 2025)

Hatevolution: What Static Benchmarks Don’t Tell Us (Di Bonaventura et al., Findings 2025)

ACL

Chiara Di Bonaventura, Barbara McGillivray, Yulan He, and Albert Meroño-Peñuela. 2025. Hatevolution: What Static Benchmarks Don’t Tell Us. In Findings of the Association for Computational Linguistics: ACL 2025, pages 17695–17707, Vienna, Austria. Association for Computational Linguistics.