@inproceedings{macko-etal-2026-increasing,
title = "Increasing the Robustness of the Fine-tuned Multilingual Machine-Generated Text Detectors",
author = "Macko, Dominik and
Moro, Robert and
Srba, Ivan",
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-1.11/",
pages = "154--166",
ISBN = "979-8-89176-470-5",
abstract = "Since the proliferation of LLMs, there have been concerns about their misuse for harmful content creation and dissemination. Recent studies justify such fears, providing evidence of LLM vulnerabilities and high misuse potential. It has been shown that humans struggle to reliably distinguish high-quality machine-generated text from authentic human-written text. Therefore, it is crucial to develop automated means to accurately detect machine-generated content. While multiple detectors of machine-generated texts have been researched so far, a known issue is their low generalizability to unseen generators, domains or languages. This work addresses the problem by proposing a robustness-oriented LLM training methodology for the detection task, making the detectors more robust against obfuscation and more generalizable to out-of-distribution data. The fixed-size ablation study confirms that the gains are not simply a function of more data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="macko-etal-2026-increasing">
<titleInfo>
<title>Increasing the Robustness of the Fine-tuned Multilingual Machine-Generated Text Detectors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dominik</namePart>
<namePart type="family">Macko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Moro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Srba</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>Since the proliferation of LLMs, there have been concerns about their misuse for harmful content creation and dissemination. Recent studies justify such fears, providing evidence of LLM vulnerabilities and high misuse potential. It has been shown that humans struggle to reliably distinguish high-quality machine-generated text from authentic human-written text. Therefore, it is crucial to develop automated means to accurately detect machine-generated content. While multiple detectors of machine-generated texts have been researched so far, a known issue is their low generalizability to unseen generators, domains or languages. This work addresses the problem by proposing a robustness-oriented LLM training methodology for the detection task, making the detectors more robust against obfuscation and more generalizable to out-of-distribution data. The fixed-size ablation study confirms that the gains are not simply a function of more data.</abstract>
<identifier type="citekey">macko-etal-2026-increasing</identifier>
<location>
<url>https://aclanthology.org/2026.wnut-1.11/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>154</start>
<end>166</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Increasing the Robustness of the Fine-tuned Multilingual Machine-Generated Text Detectors
%A Macko, Dominik
%A Moro, Robert
%A Srba, Ivan
%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 macko-etal-2026-increasing
%X Since the proliferation of LLMs, there have been concerns about their misuse for harmful content creation and dissemination. Recent studies justify such fears, providing evidence of LLM vulnerabilities and high misuse potential. It has been shown that humans struggle to reliably distinguish high-quality machine-generated text from authentic human-written text. Therefore, it is crucial to develop automated means to accurately detect machine-generated content. While multiple detectors of machine-generated texts have been researched so far, a known issue is their low generalizability to unseen generators, domains or languages. This work addresses the problem by proposing a robustness-oriented LLM training methodology for the detection task, making the detectors more robust against obfuscation and more generalizable to out-of-distribution data. The fixed-size ablation study confirms that the gains are not simply a function of more data.
%U https://aclanthology.org/2026.wnut-1.11/
%P 154-166
Markdown (Informal)
[Increasing the Robustness of the Fine-tuned Multilingual Machine-Generated Text Detectors](https://aclanthology.org/2026.wnut-1.11/) (Macko et al., WNUT 2026)
ACL