Multi-author style detection with stylistic embeddings

Man-Ling Sung; Chak-Fai Li; Damianos Karakos; Frederick E. Bernardin III; Brian Ulicny

Multi-author style detection with stylistic embeddings

Man-Ling Sung, Chak-Fai Li, Damianos Karakos, Frederick E. Bernardin III, Brian Ulicny

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 ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

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

We investigate the use of Large Language Models (LLMs) in multi-author style change detection. Using off-the-shelf LLMs or supervised fine-tuning solely within the target domain fails to yield effective features; for this reason, we propose cross-domain transfer learning with LLM-based embeddings fine-tuned for authorship verification. We fine-tune Mistral-7B embedding model and compare it with DeBERTa, used in the the state-of-the-art (SOTA) systems in PAN-25 multi-author writing style analysis challenge. Results show that DeBERTa and Mistral excel in different user-generated text scenarios. We exploit this diversity by combining both embeddings, leading to more effective style change detection.

Anthology ID:: 2026.wnut-1.13
Volume:: Proceedings of the 11th Workshop on Natural User-generated Text
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: JinYeong Bak, Rob van der Goot, Hyeju Jang, Weerayut Buaphet, Alan Ramponi, Wei Xu, Alan Ritter
Venues:: WNUT | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 182–194
Language:
URL:: https://aclanthology.org/2026.wnut-1.13/
DOI:
Bibkey:
Cite (ACL):: Man-Ling Sung, Chak-Fai Li, Damianos Karakos, Frederick E. Bernardin III, and Brian Ulicny. 2026. Multi-author style detection with stylistic embeddings. In Proceedings of the 11th Workshop on Natural User-generated Text, pages 182–194, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Multi-author style detection with stylistic embeddings (Sung et al., WNUT 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.wnut-1.13.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{sung-etal-2026-multi,
    title = "Multi-author style detection with stylistic embeddings",
    author = "Sung, Man-Ling  and
      Li, Chak-Fai  and
      Karakos, Damianos  and
      Bernardin III, Frederick E.  and
      Ulicny, Brian",
    editor = "Bak, JinYeong  and
      van der Goot, Rob  and
      Jang, Hyeju  and
      Buaphet, Weerayut  and
      Ramponi, Alan  and
      Xu, Wei  and
      Ritter, Alan",
    booktitle = "Proceedings of the 11th Workshop on Natural User-generated Text",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.wnut-1.13/",
    pages = "182--194",
    ISBN = "979-8-89176-470-5",
    abstract = "We investigate the use of Large Language Models (LLMs) in multi-author style change detection. Using off-the-shelf LLMs or supervised fine-tuning solely within the target domain fails to yield effective features; for this reason, we propose cross-domain transfer learning with LLM-based embeddings fine-tuned for authorship verification. We fine-tune Mistral-7B embedding model and compare it with DeBERTa, used in the the state-of-the-art (SOTA) systems in PAN-25 multi-author writing style analysis challenge. Results show that DeBERTa and Mistral excel in different user-generated text scenarios. We exploit this diversity by combining both embeddings, leading to more effective style change detection."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sung-etal-2026-multi">
    <titleInfo>
        <title>Multi-author style detection with stylistic embeddings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Man-Ling</namePart>
        <namePart type="family">Sung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chak-Fai</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Damianos</namePart>
        <namePart type="family">Karakos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Frederick</namePart>
        <namePart type="given">E</namePart>
        <namePart type="family">Bernardin III</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Brian</namePart>
        <namePart type="family">Ulicny</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 11th Workshop on Natural User-generated Text</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">JinYeong</namePart>
            <namePart type="family">Bak</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rob</namePart>
            <namePart type="family">van der Goot</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hyeju</namePart>
            <namePart type="family">Jang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Weerayut</namePart>
            <namePart type="family">Buaphet</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alan</namePart>
            <namePart type="family">Ramponi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Wei</namePart>
            <namePart type="family">Xu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alan</namePart>
            <namePart type="family">Ritter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-470-5</identifier>
    </relatedItem>
    <abstract>We investigate the use of Large Language Models (LLMs) in multi-author style change detection. Using off-the-shelf LLMs or supervised fine-tuning solely within the target domain fails to yield effective features; for this reason, we propose cross-domain transfer learning with LLM-based embeddings fine-tuned for authorship verification. We fine-tune Mistral-7B embedding model and compare it with DeBERTa, used in the the state-of-the-art (SOTA) systems in PAN-25 multi-author writing style analysis challenge. Results show that DeBERTa and Mistral excel in different user-generated text scenarios. We exploit this diversity by combining both embeddings, leading to more effective style change detection.</abstract>
    <identifier type="citekey">sung-etal-2026-multi</identifier>
    <location>
        <url>https://aclanthology.org/2026.wnut-1.13/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>182</start>
            <end>194</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Multi-author style detection with stylistic embeddings
%A Sung, Man-Ling
%A Li, Chak-Fai
%A Karakos, Damianos
%A Bernardin III, Frederick E.
%A Ulicny, Brian
%Y Bak, JinYeong
%Y van der Goot, Rob
%Y Jang, Hyeju
%Y Buaphet, Weerayut
%Y Ramponi, Alan
%Y Xu, Wei
%Y Ritter, Alan
%S Proceedings of the 11th Workshop on Natural User-generated Text
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-470-5
%F sung-etal-2026-multi
%X We investigate the use of Large Language Models (LLMs) in multi-author style change detection. Using off-the-shelf LLMs or supervised fine-tuning solely within the target domain fails to yield effective features; for this reason, we propose cross-domain transfer learning with LLM-based embeddings fine-tuned for authorship verification. We fine-tune Mistral-7B embedding model and compare it with DeBERTa, used in the the state-of-the-art (SOTA) systems in PAN-25 multi-author writing style analysis challenge. Results show that DeBERTa and Mistral excel in different user-generated text scenarios. We exploit this diversity by combining both embeddings, leading to more effective style change detection.
%U https://aclanthology.org/2026.wnut-1.13/
%P 182-194

Download as File

Markdown (Informal)

[Multi-author style detection with stylistic embeddings](https://aclanthology.org/2026.wnut-1.13/) (Sung et al., WNUT 2026)

Multi-author style detection with stylistic embeddings (Sung et al., WNUT 2026)

ACL

Man-Ling Sung, Chak-Fai Li, Damianos Karakos, Frederick E. Bernardin III, and Brian Ulicny. 2026. Multi-author style detection with stylistic embeddings. In Proceedings of the 11th Workshop on Natural User-generated Text, pages 182–194, Budapest, Hungary. Association for Computational Linguistics.