@inproceedings{chowdhury-etal-2025-genai,
title = "{G}en{AI} Content Detection Task 2: {AI} vs. Human {--} Academic Essay Authenticity Challenge",
author = "Chowdhury, Shammur Absar and
Almerekhi, Hind and
Kutlu, Mucahid and
Kele{\c{s}}, Kaan Efe and
Ahmad, Fatema and
Mohiuddin, Tasnim and
Mikros, George and
Alam, Firoj",
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-1.37/",
pages = "323--333",
abstract = "This paper presents a comprehensive overview of the first edition of the Academic Essay Authenticity Challenge, organized as part of the GenAI Content Detection shared tasks collocated with COLING 2025. This challenge focuses on detecting machine-generated \textit{vs} human-authored essays for academic purposes. The task is defined as follows: \textit{{\textquotedblleft}Given an essay, identify whether it is generated by a machine or authored by a human.{\textquotedblright}} The challenge involves two languages: English and Arabic. During the evaluation phase, 25 teams submitted systems for English and 21 teams for Arabic, reflecting substantial interest in the task. Finally, five teams submitted system description papers. The majority of submissions utilized fine-tuned transformer-based models, with one team employing Large Language Models (LLMs) such as Llama 2 and Llama 3. This paper outlines the task formulation, details the dataset construction process, and explains the evaluation framework. Additionally, we present a summary of the approaches adopted by participating teams. Nearly all submitted systems outperformed the n-gram-based baseline, with the top-performing systems achieving F1 scores exceeding 0.98 for both languages, indicating significant progress in the detection of machine-generated text."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chowdhury-etal-2025-genai">
<titleInfo>
<title>GenAI Content Detection Task 2: AI vs. Human – Academic Essay Authenticity Challenge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hind</namePart>
<namePart type="family">Almerekhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mucahid</namePart>
<namePart type="family">Kutlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaan</namePart>
<namePart type="given">Efe</namePart>
<namePart type="family">Keleş</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fatema</namePart>
<namePart type="family">Ahmad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tasnim</namePart>
<namePart type="family">Mohiuddin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Mikros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</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 comprehensive overview of the first edition of the Academic Essay Authenticity Challenge, organized as part of the GenAI Content Detection shared tasks collocated with COLING 2025. This challenge focuses on detecting machine-generated vs human-authored essays for academic purposes. The task is defined as follows: “Given an essay, identify whether it is generated by a machine or authored by a human.” The challenge involves two languages: English and Arabic. During the evaluation phase, 25 teams submitted systems for English and 21 teams for Arabic, reflecting substantial interest in the task. Finally, five teams submitted system description papers. The majority of submissions utilized fine-tuned transformer-based models, with one team employing Large Language Models (LLMs) such as Llama 2 and Llama 3. This paper outlines the task formulation, details the dataset construction process, and explains the evaluation framework. Additionally, we present a summary of the approaches adopted by participating teams. Nearly all submitted systems outperformed the n-gram-based baseline, with the top-performing systems achieving F1 scores exceeding 0.98 for both languages, indicating significant progress in the detection of machine-generated text.</abstract>
<identifier type="citekey">chowdhury-etal-2025-genai</identifier>
<location>
<url>https://aclanthology.org/2025.genaidetect-1.37/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>323</start>
<end>333</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GenAI Content Detection Task 2: AI vs. Human – Academic Essay Authenticity Challenge
%A Chowdhury, Shammur Absar
%A Almerekhi, Hind
%A Kutlu, Mucahid
%A Keleş, Kaan Efe
%A Ahmad, Fatema
%A Mohiuddin, Tasnim
%A Mikros, George
%A Alam, Firoj
%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 chowdhury-etal-2025-genai
%X This paper presents a comprehensive overview of the first edition of the Academic Essay Authenticity Challenge, organized as part of the GenAI Content Detection shared tasks collocated with COLING 2025. This challenge focuses on detecting machine-generated vs human-authored essays for academic purposes. The task is defined as follows: “Given an essay, identify whether it is generated by a machine or authored by a human.” The challenge involves two languages: English and Arabic. During the evaluation phase, 25 teams submitted systems for English and 21 teams for Arabic, reflecting substantial interest in the task. Finally, five teams submitted system description papers. The majority of submissions utilized fine-tuned transformer-based models, with one team employing Large Language Models (LLMs) such as Llama 2 and Llama 3. This paper outlines the task formulation, details the dataset construction process, and explains the evaluation framework. Additionally, we present a summary of the approaches adopted by participating teams. Nearly all submitted systems outperformed the n-gram-based baseline, with the top-performing systems achieving F1 scores exceeding 0.98 for both languages, indicating significant progress in the detection of machine-generated text.
%U https://aclanthology.org/2025.genaidetect-1.37/
%P 323-333
Markdown (Informal)
[GenAI Content Detection Task 2: AI vs. Human – Academic Essay Authenticity Challenge](https://aclanthology.org/2025.genaidetect-1.37/) (Chowdhury et al., GenAIDetect 2025)
ACL
- Shammur Absar Chowdhury, Hind Almerekhi, Mucahid Kutlu, Kaan Efe Keleş, Fatema Ahmad, Tasnim Mohiuddin, George Mikros, and Firoj Alam. 2025. GenAI Content Detection Task 2: AI vs. Human – Academic Essay Authenticity Challenge. In Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect), pages 323–333, Abu Dhabi, UAE. International Conference on Computational Linguistics.