@inproceedings{dhaini-etal-2023-detecting,
title = "Detecting {C}hat{GPT}: A Survey of the State of Detecting {C}hat{GPT}-Generated Text",
author = "Dhaini, Mahdi and
Poelman, Wessel and
Erdogan, Ege",
editor = "Hardalov, Momchil and
Kancheva, Zara and
Velichkov, Boris and
Nikolova-Koleva, Ivelina and
Slavcheva, Milena",
booktitle = "Proceedings of the 8th Student Research Workshop associated with the International Conference Recent Advances in Natural Language Processing",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.ranlp-stud.1",
pages = "1--12",
abstract = "While recent advancements in the capabilities and widespread accessibility of generative language models, such as ChatGPT (OpenAI, 2022), have brought about various benefits by generating fluent human-like text, the task of distinguishing between human- and large language model (LLM) generated text has emerged as a crucial problem. These models can potentially deceive by generating artificial text that appears to be human-generated. This issue is particularly significant in domains such as law, education, and science, where ensuring the integrity of text is of the utmost importance. This survey provides an overview of the current approaches employed to differentiate between texts generated by humans and ChatGPT. We present an account of the different datasets constructed for detecting ChatGPT-generated text, the various methods utilized, what qualitative analyses into the characteristics of human versus ChatGPT-generated text have been performed, and finally, summarize our findings into general insights.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dhaini-etal-2023-detecting">
<titleInfo>
<title>Detecting ChatGPT: A Survey of the State of Detecting ChatGPT-Generated Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahdi</namePart>
<namePart type="family">Dhaini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wessel</namePart>
<namePart type="family">Poelman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ege</namePart>
<namePart type="family">Erdogan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Student Research Workshop associated with the International Conference Recent Advances in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Momchil</namePart>
<namePart type="family">Hardalov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zara</namePart>
<namePart type="family">Kancheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boris</namePart>
<namePart type="family">Velichkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivelina</namePart>
<namePart type="family">Nikolova-Koleva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milena</namePart>
<namePart type="family">Slavcheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While recent advancements in the capabilities and widespread accessibility of generative language models, such as ChatGPT (OpenAI, 2022), have brought about various benefits by generating fluent human-like text, the task of distinguishing between human- and large language model (LLM) generated text has emerged as a crucial problem. These models can potentially deceive by generating artificial text that appears to be human-generated. This issue is particularly significant in domains such as law, education, and science, where ensuring the integrity of text is of the utmost importance. This survey provides an overview of the current approaches employed to differentiate between texts generated by humans and ChatGPT. We present an account of the different datasets constructed for detecting ChatGPT-generated text, the various methods utilized, what qualitative analyses into the characteristics of human versus ChatGPT-generated text have been performed, and finally, summarize our findings into general insights.</abstract>
<identifier type="citekey">dhaini-etal-2023-detecting</identifier>
<location>
<url>https://aclanthology.org/2023.ranlp-stud.1</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>1</start>
<end>12</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detecting ChatGPT: A Survey of the State of Detecting ChatGPT-Generated Text
%A Dhaini, Mahdi
%A Poelman, Wessel
%A Erdogan, Ege
%Y Hardalov, Momchil
%Y Kancheva, Zara
%Y Velichkov, Boris
%Y Nikolova-Koleva, Ivelina
%Y Slavcheva, Milena
%S Proceedings of the 8th Student Research Workshop associated with the International Conference Recent Advances in Natural Language Processing
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F dhaini-etal-2023-detecting
%X While recent advancements in the capabilities and widespread accessibility of generative language models, such as ChatGPT (OpenAI, 2022), have brought about various benefits by generating fluent human-like text, the task of distinguishing between human- and large language model (LLM) generated text has emerged as a crucial problem. These models can potentially deceive by generating artificial text that appears to be human-generated. This issue is particularly significant in domains such as law, education, and science, where ensuring the integrity of text is of the utmost importance. This survey provides an overview of the current approaches employed to differentiate between texts generated by humans and ChatGPT. We present an account of the different datasets constructed for detecting ChatGPT-generated text, the various methods utilized, what qualitative analyses into the characteristics of human versus ChatGPT-generated text have been performed, and finally, summarize our findings into general insights.
%U https://aclanthology.org/2023.ranlp-stud.1
%P 1-12
Markdown (Informal)
[Detecting ChatGPT: A Survey of the State of Detecting ChatGPT-Generated Text](https://aclanthology.org/2023.ranlp-stud.1) (Dhaini et al., RANLP 2023)
ACL