@inproceedings{schaaf-etal-2026-ghostwriter,
title = "{G}host{W}riter: Hidden {AI}-Generated Texts over Multiple Languages, Domains and Generators",
author = {Schaaf, Manuel and
B{\"o}nisch, Kevin and
Mehler, Alexander},
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.823/",
doi = "10.63317/57fd7juh5zek",
pages = "10497--10516",
abstract = "The advent of Transformer-based Large Language Models (LLMs) has led to an unprecedented surge of AI-generated text (AIGT) across online platforms and academic domains. While these models exhibit near-human fluency and stylistic coherence, their widespread adoption has raised concerns about authorship integrity, research quality, and the recursive contamination of training corpora with synthetic data. These developments underscore the need for reliable AIGT detection methods and benchmark datasets, particularly for malicious or deceptive \textit{ghostwriting} scenarios where AIGT is intentionally crafted to evade detection. To address this, we present \textbf{GhostWriter}, a large-scale, bilingual (German and English), multi-generator, and multi-domain dataset for AIGT detection. The dataset comprises human- and AI-authored texts produced under domain-specific \textit{ghostwriting} conditions, including examples intentionally embedded within otherwise human-written texts to obscure their AI origin. With \textbf{GhostWriter}, we (i) aim to expand the resources available for German AIGT datasets, (ii) emphasize mixed or fused synthesizations{---}since most existing corpora are limited to the document level{---}and (iii) introduce specifically crafted malicious ghostwriting scenarios across multiple domains and generators."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schaaf-etal-2026-ghostwriter">
<titleInfo>
<title>GhostWriter: Hidden AI-Generated Texts over Multiple Languages, Domains and Generators</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Schaaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Bönisch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Mehler</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>The advent of Transformer-based Large Language Models (LLMs) has led to an unprecedented surge of AI-generated text (AIGT) across online platforms and academic domains. While these models exhibit near-human fluency and stylistic coherence, their widespread adoption has raised concerns about authorship integrity, research quality, and the recursive contamination of training corpora with synthetic data. These developments underscore the need for reliable AIGT detection methods and benchmark datasets, particularly for malicious or deceptive ghostwriting scenarios where AIGT is intentionally crafted to evade detection. To address this, we present GhostWriter, a large-scale, bilingual (German and English), multi-generator, and multi-domain dataset for AIGT detection. The dataset comprises human- and AI-authored texts produced under domain-specific ghostwriting conditions, including examples intentionally embedded within otherwise human-written texts to obscure their AI origin. With GhostWriter, we (i) aim to expand the resources available for German AIGT datasets, (ii) emphasize mixed or fused synthesizations—since most existing corpora are limited to the document level—and (iii) introduce specifically crafted malicious ghostwriting scenarios across multiple domains and generators.</abstract>
<identifier type="citekey">schaaf-etal-2026-ghostwriter</identifier>
<identifier type="doi">10.63317/57fd7juh5zek</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.823/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>10497</start>
<end>10516</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GhostWriter: Hidden AI-Generated Texts over Multiple Languages, Domains and Generators
%A Schaaf, Manuel
%A Bönisch, Kevin
%A Mehler, Alexander
%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 schaaf-etal-2026-ghostwriter
%X The advent of Transformer-based Large Language Models (LLMs) has led to an unprecedented surge of AI-generated text (AIGT) across online platforms and academic domains. While these models exhibit near-human fluency and stylistic coherence, their widespread adoption has raised concerns about authorship integrity, research quality, and the recursive contamination of training corpora with synthetic data. These developments underscore the need for reliable AIGT detection methods and benchmark datasets, particularly for malicious or deceptive ghostwriting scenarios where AIGT is intentionally crafted to evade detection. To address this, we present GhostWriter, a large-scale, bilingual (German and English), multi-generator, and multi-domain dataset for AIGT detection. The dataset comprises human- and AI-authored texts produced under domain-specific ghostwriting conditions, including examples intentionally embedded within otherwise human-written texts to obscure their AI origin. With GhostWriter, we (i) aim to expand the resources available for German AIGT datasets, (ii) emphasize mixed or fused synthesizations—since most existing corpora are limited to the document level—and (iii) introduce specifically crafted malicious ghostwriting scenarios across multiple domains and generators.
%R 10.63317/57fd7juh5zek
%U https://aclanthology.org/2026.lrec-1.823/
%U https://doi.org/10.63317/57fd7juh5zek
%P 10497-10516
Markdown (Informal)
[GhostWriter: Hidden AI-Generated Texts over Multiple Languages, Domains and Generators](https://aclanthology.org/2026.lrec-1.823/) (Schaaf et al., LREC 2026)
ACL