<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="durandard-etal-2026-evaluating">
    <titleInfo>
        <title>Evaluating Style Embeddings for Machine-Generated Text Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Noé</namePart>
        <namePart type="family">Durandard</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Saurabh</namePart>
        <namePart type="family">Dhawan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Thierry</namePart>
        <namePart type="family">Poibeau</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper, we evaluate the use of style embeddings for distinguishing machine-generated from human-written text. Style embeddings are particularly suited for this task as compared to semantic embeddings, they offer higher content-independence, and compared to feature-engineering approaches, they offer a richer and more holistic representation of writing style. We use a detection module in which texts are first embedded in high-dimensional stylistic spaces using a style encoder, and the resulting vector representations are classified using supervised methods. To optimize this detector, we evaluate the performance of a range of pre-trained public-domain style encoders paired with different supervised methods. When evaluated on MGTBench, a widely adopted benchmark, our approach matches or exceeds state-of-the-art performance metrics. It also generalizes well across various text domains and LLMs. Our findings highlight the potential, and would facilitate the use, of style embeddings as lightweight and effective components of machine-generated text detection systems.</abstract>
    <identifier type="citekey">durandard-etal-2026-evaluating</identifier>
    <identifier type="doi">10.63317/5hb2q2wfzabd</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.205/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>2619</start>
            <end>2628</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Evaluating Style Embeddings for Machine-Generated Text Detection
%A Durandard, Noé
%A Dhawan, Saurabh
%A Poibeau, Thierry
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F durandard-etal-2026-evaluating
%X In this paper, we evaluate the use of style embeddings for distinguishing machine-generated from human-written text. Style embeddings are particularly suited for this task as compared to semantic embeddings, they offer higher content-independence, and compared to feature-engineering approaches, they offer a richer and more holistic representation of writing style. We use a detection module in which texts are first embedded in high-dimensional stylistic spaces using a style encoder, and the resulting vector representations are classified using supervised methods. To optimize this detector, we evaluate the performance of a range of pre-trained public-domain style encoders paired with different supervised methods. When evaluated on MGTBench, a widely adopted benchmark, our approach matches or exceeds state-of-the-art performance metrics. It also generalizes well across various text domains and LLMs. Our findings highlight the potential, and would facilitate the use, of style embeddings as lightweight and effective components of machine-generated text detection systems.
%R 10.63317/5hb2q2wfzabd
%U https://aclanthology.org/2026.lrec-1.205/
%U https://doi.org/10.63317/5hb2q2wfzabd
%P 2619-2628

Markdown (Informal)

[Evaluating Style Embeddings for Machine-Generated Text Detection](https://aclanthology.org/2026.lrec-1.205/) (Durandard et al., LREC 2026)

• Evaluating Style Embeddings for Machine-Generated Text Detection (Durandard et al., LREC 2026)

ACL

• Noé Durandard, Saurabh Dhawan, and Thierry Poibeau. 2026. Evaluating Style Embeddings for Machine-Generated Text Detection. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 2619–2628, Palma de Mallorca, Spain. ELRA Language Resource Association.