@inproceedings{dubois-etal-2025-mosaic,
title = "{MOSAIC} at {GENAI} Detection Task 3 : Zero-Shot Detection Using an Ensemble of Models",
author = "Dubois, Matthieu and
Yvon, Fran{\c{c}}ois and
Piantanida, Pablo",
editor = "Alam, Firoj and
Nakov, Preslav and
Habash, Nizar and
Gurevych, Iryna and
Chowdhury, Shammur and
Shelmanov, Artem and
Wang, Yuxia and
Artemova, Ekaterina and
Kutlu, Mucahid and
Mikros, George",
booktitle = "Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "International Conference on Computational Linguistics",
url = "https://aclanthology.org/2025.genaidetect-1.44/",
pages = "371--376",
abstract = "MOSAIC introduces a new ensemble approach that combines several detector models to spot AI-generated texts. The method enhances the reliability of detection by integrating insights from multiple models, thus addressing the limitations of using a single detector model which often results in performance brittleness. This approach also involves using a theoretically grounded algorithm to minimize the worst-case expected encoding size across models, thereby optimizing the detection process. In this submission, we report evaluation results on the RAID benchmark, a comprehensive English-centric testbed for machine-generated texts. These results were obtained in the context of the {\textquotedblleft}Cross-domain Machine-Generated Text Detection{\textquotedblright} shared task. We show that our model can be competitive for a variety of domains and generator models, but that it can be challenged by adversarial attacks and by changes in the text generation strategy."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dubois-etal-2025-mosaic">
<titleInfo>
<title>MOSAIC at GENAI Detection Task 3 : Zero-Shot Detection Using an Ensemble of Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthieu</namePart>
<namePart type="family">Dubois</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Yvon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pablo</namePart>
<namePart type="family">Piantanida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Shelmanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxia</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Artemova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mucahid</namePart>
<namePart type="family">Kutlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Mikros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Conference on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>MOSAIC introduces a new ensemble approach that combines several detector models to spot AI-generated texts. The method enhances the reliability of detection by integrating insights from multiple models, thus addressing the limitations of using a single detector model which often results in performance brittleness. This approach also involves using a theoretically grounded algorithm to minimize the worst-case expected encoding size across models, thereby optimizing the detection process. In this submission, we report evaluation results on the RAID benchmark, a comprehensive English-centric testbed for machine-generated texts. These results were obtained in the context of the “Cross-domain Machine-Generated Text Detection” shared task. We show that our model can be competitive for a variety of domains and generator models, but that it can be challenged by adversarial attacks and by changes in the text generation strategy.</abstract>
<identifier type="citekey">dubois-etal-2025-mosaic</identifier>
<location>
<url>https://aclanthology.org/2025.genaidetect-1.44/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>371</start>
<end>376</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MOSAIC at GENAI Detection Task 3 : Zero-Shot Detection Using an Ensemble of Models
%A Dubois, Matthieu
%A Yvon, François
%A Piantanida, Pablo
%Y Alam, Firoj
%Y Nakov, Preslav
%Y Habash, Nizar
%Y Gurevych, Iryna
%Y Chowdhury, Shammur
%Y Shelmanov, Artem
%Y Wang, Yuxia
%Y Artemova, Ekaterina
%Y Kutlu, Mucahid
%Y Mikros, George
%S Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)
%D 2025
%8 January
%I International Conference on Computational Linguistics
%C Abu Dhabi, UAE
%F dubois-etal-2025-mosaic
%X MOSAIC introduces a new ensemble approach that combines several detector models to spot AI-generated texts. The method enhances the reliability of detection by integrating insights from multiple models, thus addressing the limitations of using a single detector model which often results in performance brittleness. This approach also involves using a theoretically grounded algorithm to minimize the worst-case expected encoding size across models, thereby optimizing the detection process. In this submission, we report evaluation results on the RAID benchmark, a comprehensive English-centric testbed for machine-generated texts. These results were obtained in the context of the “Cross-domain Machine-Generated Text Detection” shared task. We show that our model can be competitive for a variety of domains and generator models, but that it can be challenged by adversarial attacks and by changes in the text generation strategy.
%U https://aclanthology.org/2025.genaidetect-1.44/
%P 371-376
Markdown (Informal)
[MOSAIC at GENAI Detection Task 3 : Zero-Shot Detection Using an Ensemble of Models](https://aclanthology.org/2025.genaidetect-1.44/) (Dubois et al., GenAIDetect 2025)
ACL