@inproceedings{li-etal-2024-mage,
title = "{MAGE}: Machine-generated Text Detection in the Wild",
author = "Li, Yafu and
Li, Qintong and
Cui, Leyang and
Bi, Wei and
Wang, Zhilin and
Wang, Longyue and
Yang, Linyi and
Shi, Shuming and
Zhang, Yue",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.3",
pages = "36--53",
abstract = "Large language models (LLMs) have achieved human-level text generation, emphasizing the need for effective deepfake text detection to mitigate risks like the spread of fake news and plagiarism. Existing research has been constrained by evaluating detection methods o specific domains or particular language models. In practical scenarios, however, the detector faces texts from various domains or LLMs without knowing their sources. To this end, we build a comprehensive testbed by gathering texts from diverse human writings and deepfake texts generated by different LLMs. Empirical results on mainstream detection methods demonstrate the difficulties associated with detecting deepfake text in a wide-ranging testbed, particularly in out-of-distribution scenarios. Such difficulties align with the diminishing linguistic differences between the two text sources. Despite challenges, the top-performing detector can identify 84.12{\%} out-of-domain texts generated by a new LLM, indicating the feasibility for application scenarios.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-mage">
<titleInfo>
<title>MAGE: Machine-generated Text Detection in the Wild</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yafu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qintong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leyang</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Bi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhilin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Longyue</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuming</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) have achieved human-level text generation, emphasizing the need for effective deepfake text detection to mitigate risks like the spread of fake news and plagiarism. Existing research has been constrained by evaluating detection methods o specific domains or particular language models. In practical scenarios, however, the detector faces texts from various domains or LLMs without knowing their sources. To this end, we build a comprehensive testbed by gathering texts from diverse human writings and deepfake texts generated by different LLMs. Empirical results on mainstream detection methods demonstrate the difficulties associated with detecting deepfake text in a wide-ranging testbed, particularly in out-of-distribution scenarios. Such difficulties align with the diminishing linguistic differences between the two text sources. Despite challenges, the top-performing detector can identify 84.12% out-of-domain texts generated by a new LLM, indicating the feasibility for application scenarios.</abstract>
<identifier type="citekey">li-etal-2024-mage</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.3</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>36</start>
<end>53</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MAGE: Machine-generated Text Detection in the Wild
%A Li, Yafu
%A Li, Qintong
%A Cui, Leyang
%A Bi, Wei
%A Wang, Zhilin
%A Wang, Longyue
%A Yang, Linyi
%A Shi, Shuming
%A Zhang, Yue
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F li-etal-2024-mage
%X Large language models (LLMs) have achieved human-level text generation, emphasizing the need for effective deepfake text detection to mitigate risks like the spread of fake news and plagiarism. Existing research has been constrained by evaluating detection methods o specific domains or particular language models. In practical scenarios, however, the detector faces texts from various domains or LLMs without knowing their sources. To this end, we build a comprehensive testbed by gathering texts from diverse human writings and deepfake texts generated by different LLMs. Empirical results on mainstream detection methods demonstrate the difficulties associated with detecting deepfake text in a wide-ranging testbed, particularly in out-of-distribution scenarios. Such difficulties align with the diminishing linguistic differences between the two text sources. Despite challenges, the top-performing detector can identify 84.12% out-of-domain texts generated by a new LLM, indicating the feasibility for application scenarios.
%U https://aclanthology.org/2024.acl-long.3
%P 36-53
Markdown (Informal)
[MAGE: Machine-generated Text Detection in the Wild](https://aclanthology.org/2024.acl-long.3) (Li et al., ACL 2024)
ACL
- Yafu Li, Qintong Li, Leyang Cui, Wei Bi, Zhilin Wang, Longyue Wang, Linyi Yang, Shuming Shi, and Yue Zhang. 2024. MAGE: Machine-generated Text Detection in the Wild. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 36–53, Bangkok, Thailand. Association for Computational Linguistics.