@inproceedings{alsmadi-2025-integrityai,
title = "{I}ntegrity{AI} at {G}en{AI} Detection Task 2: Detecting Machine-Generated Academic Essays in {E}nglish and {A}rabic Using {ELECTRA} and Stylometry",
author = "ALSmadi, Mohammad",
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-1.31/",
pages = "284--289",
abstract = "We present a robust system for detecting machine-generated academic essays, leveraging pre-trained, transformer-based models specifically tailored for both English and Arabic texts. Our primary approach utilizes ELECTRA-Small for English and AraELECTRA-Base for Arabic, fine-tuned to deliver high performance while balancing computational efficiency. By incorporating stylometric features, such as word count, sentence length, and vocabulary richness, our models excel at distinguishing between human-written and AI-generated content. Proposed models achieved excellent results with an F1- score of 99.7{\%}, ranking second among of 26 teams in the English subtask, and 98.4{\%}, finishing first out of 23 teams in the Arabic one. Main Contributions include: (1) We develop lightweight and efficient models using ELECTRA-Small and AraELECTRA-Base, achieving an impressive F1-score of 98.5{\%} on the English dataset and 98.4{\%} on the Arabic dataset. This demonstrates the power of combining transformer-based architectures with stylometric analysis. (2) We optimize our system to maintain high performance while being computationally efficient, making it suitable for deployment on GPUs with moderate memory capacity. (3) Additionally, we tested larger models, such as ELECTRA-Large, achieving an even higher F1-score of 99.7{\%} on the English dataset, highlighting the potential for further accuracy gains when using more computationally intensive models."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alsmadi-2025-integrityai">
<titleInfo>
<title>IntegrityAI at GenAI Detection Task 2: Detecting Machine-Generated Academic Essays in English and Arabic Using ELECTRA and Stylometry</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">ALSmadi</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>We present a robust system for detecting machine-generated academic essays, leveraging pre-trained, transformer-based models specifically tailored for both English and Arabic texts. Our primary approach utilizes ELECTRA-Small for English and AraELECTRA-Base for Arabic, fine-tuned to deliver high performance while balancing computational efficiency. By incorporating stylometric features, such as word count, sentence length, and vocabulary richness, our models excel at distinguishing between human-written and AI-generated content. Proposed models achieved excellent results with an F1- score of 99.7%, ranking second among of 26 teams in the English subtask, and 98.4%, finishing first out of 23 teams in the Arabic one. Main Contributions include: (1) We develop lightweight and efficient models using ELECTRA-Small and AraELECTRA-Base, achieving an impressive F1-score of 98.5% on the English dataset and 98.4% on the Arabic dataset. This demonstrates the power of combining transformer-based architectures with stylometric analysis. (2) We optimize our system to maintain high performance while being computationally efficient, making it suitable for deployment on GPUs with moderate memory capacity. (3) Additionally, we tested larger models, such as ELECTRA-Large, achieving an even higher F1-score of 99.7% on the English dataset, highlighting the potential for further accuracy gains when using more computationally intensive models.</abstract>
<identifier type="citekey">alsmadi-2025-integrityai</identifier>
<location>
<url>https://aclanthology.org/2025.genaidetect-1.31/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>284</start>
<end>289</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IntegrityAI at GenAI Detection Task 2: Detecting Machine-Generated Academic Essays in English and Arabic Using ELECTRA and Stylometry
%A ALSmadi, Mohammad
%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 alsmadi-2025-integrityai
%X We present a robust system for detecting machine-generated academic essays, leveraging pre-trained, transformer-based models specifically tailored for both English and Arabic texts. Our primary approach utilizes ELECTRA-Small for English and AraELECTRA-Base for Arabic, fine-tuned to deliver high performance while balancing computational efficiency. By incorporating stylometric features, such as word count, sentence length, and vocabulary richness, our models excel at distinguishing between human-written and AI-generated content. Proposed models achieved excellent results with an F1- score of 99.7%, ranking second among of 26 teams in the English subtask, and 98.4%, finishing first out of 23 teams in the Arabic one. Main Contributions include: (1) We develop lightweight and efficient models using ELECTRA-Small and AraELECTRA-Base, achieving an impressive F1-score of 98.5% on the English dataset and 98.4% on the Arabic dataset. This demonstrates the power of combining transformer-based architectures with stylometric analysis. (2) We optimize our system to maintain high performance while being computationally efficient, making it suitable for deployment on GPUs with moderate memory capacity. (3) Additionally, we tested larger models, such as ELECTRA-Large, achieving an even higher F1-score of 99.7% on the English dataset, highlighting the potential for further accuracy gains when using more computationally intensive models.
%U https://aclanthology.org/2025.genaidetect-1.31/
%P 284-289
Markdown (Informal)
[IntegrityAI at GenAI Detection Task 2: Detecting Machine-Generated Academic Essays in English and Arabic Using ELECTRA and Stylometry](https://aclanthology.org/2025.genaidetect-1.31/) (ALSmadi, GenAIDetect 2025)
ACL