@inproceedings{zhu-etal-2023-beat,
title = "Beat {LLM}s at Their Own Game: Zero-Shot {LLM}-Generated Text Detection via Querying {C}hat{GPT}",
author = "Zhu, Biru and
Yuan, Lifan and
Cui, Ganqu and
Chen, Yangyi and
Fu, Chong and
He, Bingxiang and
Deng, Yangdong and
Liu, Zhiyuan and
Sun, Maosong and
Gu, Ming",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.463",
doi = "10.18653/v1/2023.emnlp-main.463",
pages = "7470--7483",
abstract = "Large language models (LLMs), e.g., ChatGPT, have revolutionized the domain of natural language processing because of their excellent performance on various tasks. Despite their great potential, LLMs also incur serious concerns as they are likely to be misused. There are already reported cases of academic cheating by using LLMs. Thus, it is a pressing problem to identify LLM-generated texts. In this work, we design a zero-shot black-box method for detecting LLM-generated texts. The key idea is to revise the text to be detected using the ChatGPT model. Our method is based on the intuition that the ChatGPT model will make fewer revisions to LLM-generated texts than it does to human-written texts, because the texts generated by LLMs are more in accord with the generation logic and statistical patterns learned by LLMs like ChatGPT. Thus, if the text to be detected and its ChatGPT-revised version have a higher degree of similarity, the text is more likely to be LLM-generated. Extensive experiments on various datasets and tasks show that our method can effectively detect LLM-generated texts. Moreover, compared with other detection methods, our method has better generalization ability and is more stable across various datasets. The codes are publicly available at https://github.com/thunlp/LLM-generated-text-detection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2023-beat">
<titleInfo>
<title>Beat LLMs at Their Own Game: Zero-Shot LLM-Generated Text Detection via Querying ChatGPT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Biru</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifan</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ganqu</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yangyi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chong</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bingxiang</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yangdong</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs), e.g., ChatGPT, have revolutionized the domain of natural language processing because of their excellent performance on various tasks. Despite their great potential, LLMs also incur serious concerns as they are likely to be misused. There are already reported cases of academic cheating by using LLMs. Thus, it is a pressing problem to identify LLM-generated texts. In this work, we design a zero-shot black-box method for detecting LLM-generated texts. The key idea is to revise the text to be detected using the ChatGPT model. Our method is based on the intuition that the ChatGPT model will make fewer revisions to LLM-generated texts than it does to human-written texts, because the texts generated by LLMs are more in accord with the generation logic and statistical patterns learned by LLMs like ChatGPT. Thus, if the text to be detected and its ChatGPT-revised version have a higher degree of similarity, the text is more likely to be LLM-generated. Extensive experiments on various datasets and tasks show that our method can effectively detect LLM-generated texts. Moreover, compared with other detection methods, our method has better generalization ability and is more stable across various datasets. The codes are publicly available at https://github.com/thunlp/LLM-generated-text-detection.</abstract>
<identifier type="citekey">zhu-etal-2023-beat</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.463</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.463</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>7470</start>
<end>7483</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beat LLMs at Their Own Game: Zero-Shot LLM-Generated Text Detection via Querying ChatGPT
%A Zhu, Biru
%A Yuan, Lifan
%A Cui, Ganqu
%A Chen, Yangyi
%A Fu, Chong
%A He, Bingxiang
%A Deng, Yangdong
%A Liu, Zhiyuan
%A Sun, Maosong
%A Gu, Ming
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhu-etal-2023-beat
%X Large language models (LLMs), e.g., ChatGPT, have revolutionized the domain of natural language processing because of their excellent performance on various tasks. Despite their great potential, LLMs also incur serious concerns as they are likely to be misused. There are already reported cases of academic cheating by using LLMs. Thus, it is a pressing problem to identify LLM-generated texts. In this work, we design a zero-shot black-box method for detecting LLM-generated texts. The key idea is to revise the text to be detected using the ChatGPT model. Our method is based on the intuition that the ChatGPT model will make fewer revisions to LLM-generated texts than it does to human-written texts, because the texts generated by LLMs are more in accord with the generation logic and statistical patterns learned by LLMs like ChatGPT. Thus, if the text to be detected and its ChatGPT-revised version have a higher degree of similarity, the text is more likely to be LLM-generated. Extensive experiments on various datasets and tasks show that our method can effectively detect LLM-generated texts. Moreover, compared with other detection methods, our method has better generalization ability and is more stable across various datasets. The codes are publicly available at https://github.com/thunlp/LLM-generated-text-detection.
%R 10.18653/v1/2023.emnlp-main.463
%U https://aclanthology.org/2023.emnlp-main.463
%U https://doi.org/10.18653/v1/2023.emnlp-main.463
%P 7470-7483
Markdown (Informal)
[Beat LLMs at Their Own Game: Zero-Shot LLM-Generated Text Detection via Querying ChatGPT](https://aclanthology.org/2023.emnlp-main.463) (Zhu et al., EMNLP 2023)
ACL
- Biru Zhu, Lifan Yuan, Ganqu Cui, Yangyi Chen, Chong Fu, Bingxiang He, Yangdong Deng, Zhiyuan Liu, Maosong Sun, and Ming Gu. 2023. Beat LLMs at Their Own Game: Zero-Shot LLM-Generated Text Detection via Querying ChatGPT. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7470–7483, Singapore. Association for Computational Linguistics.