@inproceedings{strebeyko-etal-2026-smigiel,
title = "{\'S}migiel Dataset: Laying Foundations for Investigating Machine-Generated Text Detection in {P}olish",
author = "Strebeyko, Jakub and
Wr{\'o}blewska, Alina and
Przyby{\l}a, Piotr",
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-1.828/",
doi = "10.63317/3p7ghe9pfm8v",
pages = "10556--10568",
abstract = "We present {\'S}migiel, the first open dataset for training and evaluating machine-generated text (MGT) in Polish. The dataset includes a collection of human-written text fragments from six domains, which are used to prompt text generation by eight language models capable of producing credible Polish text. In addition to the raw corpus of over 462K generated texts, we also release a cleaned source- and domain-balanced dataset suitable for training and evaluating MGT detectors. Finally, we conduct preliminary experiments with text classifiers, showing that task difficulty depends on the text domain, the generating language model, and the availability of similar data in training. The results indicate that MGT detection in Polish can be approached with general-purpose classifiers that generalize well to new LLMs, but struggle to adapt to genres not represented in the training data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="strebeyko-etal-2026-smigiel">
<titleInfo>
<title>Śmigiel Dataset: Laying Foundations for Investigating Machine-Generated Text Detection in Polish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Strebeyko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Wróblewska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Przybyła</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>We present Śmigiel, the first open dataset for training and evaluating machine-generated text (MGT) in Polish. The dataset includes a collection of human-written text fragments from six domains, which are used to prompt text generation by eight language models capable of producing credible Polish text. In addition to the raw corpus of over 462K generated texts, we also release a cleaned source- and domain-balanced dataset suitable for training and evaluating MGT detectors. Finally, we conduct preliminary experiments with text classifiers, showing that task difficulty depends on the text domain, the generating language model, and the availability of similar data in training. The results indicate that MGT detection in Polish can be approached with general-purpose classifiers that generalize well to new LLMs, but struggle to adapt to genres not represented in the training data.</abstract>
<identifier type="citekey">strebeyko-etal-2026-smigiel</identifier>
<identifier type="doi">10.63317/3p7ghe9pfm8v</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.828/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>10556</start>
<end>10568</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Śmigiel Dataset: Laying Foundations for Investigating Machine-Generated Text Detection in Polish
%A Strebeyko, Jakub
%A Wróblewska, Alina
%A Przybyła, Piotr
%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 strebeyko-etal-2026-smigiel
%X We present Śmigiel, the first open dataset for training and evaluating machine-generated text (MGT) in Polish. The dataset includes a collection of human-written text fragments from six domains, which are used to prompt text generation by eight language models capable of producing credible Polish text. In addition to the raw corpus of over 462K generated texts, we also release a cleaned source- and domain-balanced dataset suitable for training and evaluating MGT detectors. Finally, we conduct preliminary experiments with text classifiers, showing that task difficulty depends on the text domain, the generating language model, and the availability of similar data in training. The results indicate that MGT detection in Polish can be approached with general-purpose classifiers that generalize well to new LLMs, but struggle to adapt to genres not represented in the training data.
%R 10.63317/3p7ghe9pfm8v
%U https://aclanthology.org/2026.lrec-1.828/
%U https://doi.org/10.63317/3p7ghe9pfm8v
%P 10556-10568
Markdown (Informal)
[Śmigiel Dataset: Laying Foundations for Investigating Machine-Generated Text Detection in Polish](https://aclanthology.org/2026.lrec-1.828/) (Strebeyko et al., LREC 2026)
ACL