@inproceedings{mobin-islam-2025-luxveri,
title = "{L}ux{V}eri at {G}en{AI} Detection Task 1: Inverse Perplexity Weighted Ensemble for Robust Detection of {AI}-Generated Text across {E}nglish and Multilingual Contexts",
author = "Mobin, MD. Kamrujjaman and
Islam, Md Saiful",
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-1.21/",
pages = "203--208",
abstract = "This paper presents a system developed for Task 1 of the COLING 2025 Workshop on Detecting AI-Generated Content, focusing on the binary classification of machine-generated versus human-written text. Our approach utilizes an ensemble of models, with weights assigned according to each model`s inverse perplexity, to enhance classification accuracy. For the English text detection task, we combined RoBERTa-base, RoBERTa-base with the OpenAI detector, and BERT-base-cased, achieving a Macro F1-score of 0.7458, which ranked us 12th out of 35 teams. We ensembled RemBERT, XLM-RoBERTa-base, and BERT-base-multilingual-case for the multilingual text detection task, employing the same inverse perplexity weighting technique. This resulted in a Macro F1-score of 0.7513, positioning us 4th out of 25 teams. Our results demonstrate the effectiveness of inverse perplexity weighting in improving the robustness of machine-generated text detection across both monolingual and multilingual settings, highlighting the potential of ensemble methods for this challenging task."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mobin-islam-2025-luxveri">
<titleInfo>
<title>LuxVeri at GenAI Detection Task 1: Inverse Perplexity Weighted Ensemble for Robust Detection of AI-Generated Text across English and Multilingual Contexts</title>
</titleInfo>
<name type="personal">
<namePart type="given">MD.</namePart>
<namePart type="given">Kamrujjaman</namePart>
<namePart type="family">Mobin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Saiful</namePart>
<namePart type="family">Islam</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>This paper presents a system developed for Task 1 of the COLING 2025 Workshop on Detecting AI-Generated Content, focusing on the binary classification of machine-generated versus human-written text. Our approach utilizes an ensemble of models, with weights assigned according to each model‘s inverse perplexity, to enhance classification accuracy. For the English text detection task, we combined RoBERTa-base, RoBERTa-base with the OpenAI detector, and BERT-base-cased, achieving a Macro F1-score of 0.7458, which ranked us 12th out of 35 teams. We ensembled RemBERT, XLM-RoBERTa-base, and BERT-base-multilingual-case for the multilingual text detection task, employing the same inverse perplexity weighting technique. This resulted in a Macro F1-score of 0.7513, positioning us 4th out of 25 teams. Our results demonstrate the effectiveness of inverse perplexity weighting in improving the robustness of machine-generated text detection across both monolingual and multilingual settings, highlighting the potential of ensemble methods for this challenging task.</abstract>
<identifier type="citekey">mobin-islam-2025-luxveri</identifier>
<location>
<url>https://aclanthology.org/2025.genaidetect-1.21/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>203</start>
<end>208</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LuxVeri at GenAI Detection Task 1: Inverse Perplexity Weighted Ensemble for Robust Detection of AI-Generated Text across English and Multilingual Contexts
%A Mobin, MD. Kamrujjaman
%A Islam, Md Saiful
%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 mobin-islam-2025-luxveri
%X This paper presents a system developed for Task 1 of the COLING 2025 Workshop on Detecting AI-Generated Content, focusing on the binary classification of machine-generated versus human-written text. Our approach utilizes an ensemble of models, with weights assigned according to each model‘s inverse perplexity, to enhance classification accuracy. For the English text detection task, we combined RoBERTa-base, RoBERTa-base with the OpenAI detector, and BERT-base-cased, achieving a Macro F1-score of 0.7458, which ranked us 12th out of 35 teams. We ensembled RemBERT, XLM-RoBERTa-base, and BERT-base-multilingual-case for the multilingual text detection task, employing the same inverse perplexity weighting technique. This resulted in a Macro F1-score of 0.7513, positioning us 4th out of 25 teams. Our results demonstrate the effectiveness of inverse perplexity weighting in improving the robustness of machine-generated text detection across both monolingual and multilingual settings, highlighting the potential of ensemble methods for this challenging task.
%U https://aclanthology.org/2025.genaidetect-1.21/
%P 203-208
Markdown (Informal)
[LuxVeri at GenAI Detection Task 1: Inverse Perplexity Weighted Ensemble for Robust Detection of AI-Generated Text across English and Multilingual Contexts](https://aclanthology.org/2025.genaidetect-1.21/) (Mobin & Islam, GenAIDetect 2025)
ACL