@inproceedings{yadagiri-etal-2025-cnlp-nits,
title = "{CNLP}-{NITS}-{PP} at {G}en{AI} Detection Task 2: Leveraging {D}istil{BERT} and {XLM}-{R}o{BERT}a for Multilingual {AI}-Generated Text Detection",
author = "Yadagiri, Annepaka and
Krishna, Reddi Mohana and
Pakray, Partha",
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-1.34/",
pages = "307--311",
abstract = "In today`s digital landscape, distinguishing between human-authored essays and content generated by advanced Large Language Models such as ChatGPT, GPT-4, Gemini, and LLaMa has become increasingly complex. This differentiation is essential across sectors like academia, cybersecurity, social media, and education, where the authenticity of written material is often crucial. Addressing this challenge, the COLING 2025 competition introduced Task 2, a binary classification task to separate AI-generated text from human-authored content. Using a benchmark dataset for English and Arabic, developing a methodology that fine-tuned various transformer-based neural networks, including CNN-LSTM, RNN, Bi-GRU, BERT, DistilBERT, GPT-2, and RoBERTa. Our Team CNLP-NITS-PP achieved competitive performance through meticulous hyperparameter optimization, reaching a Recall score of 0.825. Specifically, we ranked 18th in the English sub-task A with an accuracy of 0.77 and 20th in the Arabic sub-task B with an accuracy of 0.59. These results underscore the potential of transformer-based models in academic settings to detect AI-generated content effectively, laying a foundation for more advanced methods in essay authenticity verification."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yadagiri-etal-2025-cnlp-nits">
<titleInfo>
<title>CNLP-NITS-PP at GenAI Detection Task 2: Leveraging DistilBERT and XLM-RoBERTa for Multilingual AI-Generated Text Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Annepaka</namePart>
<namePart type="family">Yadagiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reddi</namePart>
<namePart type="given">Mohana</namePart>
<namePart type="family">Krishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Partha</namePart>
<namePart type="family">Pakray</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>In today‘s digital landscape, distinguishing between human-authored essays and content generated by advanced Large Language Models such as ChatGPT, GPT-4, Gemini, and LLaMa has become increasingly complex. This differentiation is essential across sectors like academia, cybersecurity, social media, and education, where the authenticity of written material is often crucial. Addressing this challenge, the COLING 2025 competition introduced Task 2, a binary classification task to separate AI-generated text from human-authored content. Using a benchmark dataset for English and Arabic, developing a methodology that fine-tuned various transformer-based neural networks, including CNN-LSTM, RNN, Bi-GRU, BERT, DistilBERT, GPT-2, and RoBERTa. Our Team CNLP-NITS-PP achieved competitive performance through meticulous hyperparameter optimization, reaching a Recall score of 0.825. Specifically, we ranked 18th in the English sub-task A with an accuracy of 0.77 and 20th in the Arabic sub-task B with an accuracy of 0.59. These results underscore the potential of transformer-based models in academic settings to detect AI-generated content effectively, laying a foundation for more advanced methods in essay authenticity verification.</abstract>
<identifier type="citekey">yadagiri-etal-2025-cnlp-nits</identifier>
<location>
<url>https://aclanthology.org/2025.genaidetect-1.34/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>307</start>
<end>311</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CNLP-NITS-PP at GenAI Detection Task 2: Leveraging DistilBERT and XLM-RoBERTa for Multilingual AI-Generated Text Detection
%A Yadagiri, Annepaka
%A Krishna, Reddi Mohana
%A Pakray, Partha
%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 yadagiri-etal-2025-cnlp-nits
%X In today‘s digital landscape, distinguishing between human-authored essays and content generated by advanced Large Language Models such as ChatGPT, GPT-4, Gemini, and LLaMa has become increasingly complex. This differentiation is essential across sectors like academia, cybersecurity, social media, and education, where the authenticity of written material is often crucial. Addressing this challenge, the COLING 2025 competition introduced Task 2, a binary classification task to separate AI-generated text from human-authored content. Using a benchmark dataset for English and Arabic, developing a methodology that fine-tuned various transformer-based neural networks, including CNN-LSTM, RNN, Bi-GRU, BERT, DistilBERT, GPT-2, and RoBERTa. Our Team CNLP-NITS-PP achieved competitive performance through meticulous hyperparameter optimization, reaching a Recall score of 0.825. Specifically, we ranked 18th in the English sub-task A with an accuracy of 0.77 and 20th in the Arabic sub-task B with an accuracy of 0.59. These results underscore the potential of transformer-based models in academic settings to detect AI-generated content effectively, laying a foundation for more advanced methods in essay authenticity verification.
%U https://aclanthology.org/2025.genaidetect-1.34/
%P 307-311
Markdown (Informal)
[CNLP-NITS-PP at GenAI Detection Task 2: Leveraging DistilBERT and XLM-RoBERTa for Multilingual AI-Generated Text Detection](https://aclanthology.org/2025.genaidetect-1.34/) (Yadagiri et al., GenAIDetect 2025)
ACL