@inproceedings{pudasaini-etal-2025-benchmarking,
title = "Benchmarking {AI} Text Detection: Assessing Detectors Against New Datasets, Evasion Tactics, and Enhanced {LLM}s",
author = "Pudasaini, Shushanta and
Miralles, Luis and
Lillis, David and
Salvador, Marisa Llorens",
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-1.4/",
pages = "68--77",
abstract = "The rapid advancement of Large Language Models (LLMs), such as GPT-4, has sparked concerns regarding academic misconduct, misinformation, and the erosion of originality. Despite the growing number of AI detection tools, their effectiveness is often undermined by sophisticated evasion tactics and the continuous evolution of LLMs. This research benchmarks the performance of leading AI detectors, including OpenAI Detector, RADAR, and ArguGPT, across a variety of text domains, evaded content, and text generated by cutting-edge LLMs. Our experiments reveal that current detection models show considerable unreliability in real-world scenarios, particularly when tested against diverse data domains and novel evasion strategies. The study underscores the need for enhanced robustness in detection systems and provides valuable insights into areas of improvement for these models. Additionally, this work lays the groundwork for future research by offering a comprehensive evaluation of existing detectors under challenging conditions, fostering a deeper understanding of their limitations. The experimental code and datasets are publicly available for further benchmarking on Github."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pudasaini-etal-2025-benchmarking">
<titleInfo>
<title>Benchmarking AI Text Detection: Assessing Detectors Against New Datasets, Evasion Tactics, and Enhanced LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shushanta</namePart>
<namePart type="family">Pudasaini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Miralles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Lillis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marisa</namePart>
<namePart type="given">Llorens</namePart>
<namePart type="family">Salvador</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>The rapid advancement of Large Language Models (LLMs), such as GPT-4, has sparked concerns regarding academic misconduct, misinformation, and the erosion of originality. Despite the growing number of AI detection tools, their effectiveness is often undermined by sophisticated evasion tactics and the continuous evolution of LLMs. This research benchmarks the performance of leading AI detectors, including OpenAI Detector, RADAR, and ArguGPT, across a variety of text domains, evaded content, and text generated by cutting-edge LLMs. Our experiments reveal that current detection models show considerable unreliability in real-world scenarios, particularly when tested against diverse data domains and novel evasion strategies. The study underscores the need for enhanced robustness in detection systems and provides valuable insights into areas of improvement for these models. Additionally, this work lays the groundwork for future research by offering a comprehensive evaluation of existing detectors under challenging conditions, fostering a deeper understanding of their limitations. The experimental code and datasets are publicly available for further benchmarking on Github.</abstract>
<identifier type="citekey">pudasaini-etal-2025-benchmarking</identifier>
<location>
<url>https://aclanthology.org/2025.genaidetect-1.4/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>68</start>
<end>77</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking AI Text Detection: Assessing Detectors Against New Datasets, Evasion Tactics, and Enhanced LLMs
%A Pudasaini, Shushanta
%A Miralles, Luis
%A Lillis, David
%A Salvador, Marisa Llorens
%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 pudasaini-etal-2025-benchmarking
%X The rapid advancement of Large Language Models (LLMs), such as GPT-4, has sparked concerns regarding academic misconduct, misinformation, and the erosion of originality. Despite the growing number of AI detection tools, their effectiveness is often undermined by sophisticated evasion tactics and the continuous evolution of LLMs. This research benchmarks the performance of leading AI detectors, including OpenAI Detector, RADAR, and ArguGPT, across a variety of text domains, evaded content, and text generated by cutting-edge LLMs. Our experiments reveal that current detection models show considerable unreliability in real-world scenarios, particularly when tested against diverse data domains and novel evasion strategies. The study underscores the need for enhanced robustness in detection systems and provides valuable insights into areas of improvement for these models. Additionally, this work lays the groundwork for future research by offering a comprehensive evaluation of existing detectors under challenging conditions, fostering a deeper understanding of their limitations. The experimental code and datasets are publicly available for further benchmarking on Github.
%U https://aclanthology.org/2025.genaidetect-1.4/
%P 68-77
Markdown (Informal)
[Benchmarking AI Text Detection: Assessing Detectors Against New Datasets, Evasion Tactics, and Enhanced LLMs](https://aclanthology.org/2025.genaidetect-1.4/) (Pudasaini et al., GenAIDetect 2025)
ACL