@inproceedings{xu-etal-2024-generalization,
title = "On the Generalization of Training-based {C}hat{GPT} Detection Methods",
author = "Xu, Han and
Ren, Jie and
He, Pengfei and
Zeng, Shenglai and
Cui, Yingqian and
Liu, Amy and
Liu, Hui and
Tang, Jiliang",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.424",
pages = "7223--7243",
abstract = "Large language models, such as ChatGPT, achieve amazing performance on various language processing tasks. However, they can also be exploited for improper purposes such as plagiarism or misinformation dissemination. Thus, there is an urgent need to detect the texts generated by LLMs. One type of most studied methods trains classification models to distinguish LLM texts from human texts. However, existing studies demonstrate the trained models may suffer from distribution shifts (during test), i.e., they are ineffective to predict the generated texts from unseen language tasks or topics which are not collected during training. In this work, we focus on ChatGPT as a representative model, and we conduct a comprehensive investigation on these methods{'} generalization behaviors under distribution shift caused by a wide range of factors, including prompts, text lengths, topics, and language tasks. To achieve this goal, we first collect a new dataset with human and ChatGPT texts, and then we conduct extensive studies on the collected dataset. Our studies unveil insightful findings that provide guidance for future methodologies and data collection strategies for LLM detection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2024-generalization">
<titleInfo>
<title>On the Generalization of Training-based ChatGPT Detection Methods</title>
</titleInfo>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengfei</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shenglai</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingqian</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiliang</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models, such as ChatGPT, achieve amazing performance on various language processing tasks. However, they can also be exploited for improper purposes such as plagiarism or misinformation dissemination. Thus, there is an urgent need to detect the texts generated by LLMs. One type of most studied methods trains classification models to distinguish LLM texts from human texts. However, existing studies demonstrate the trained models may suffer from distribution shifts (during test), i.e., they are ineffective to predict the generated texts from unseen language tasks or topics which are not collected during training. In this work, we focus on ChatGPT as a representative model, and we conduct a comprehensive investigation on these methods’ generalization behaviors under distribution shift caused by a wide range of factors, including prompts, text lengths, topics, and language tasks. To achieve this goal, we first collect a new dataset with human and ChatGPT texts, and then we conduct extensive studies on the collected dataset. Our studies unveil insightful findings that provide guidance for future methodologies and data collection strategies for LLM detection.</abstract>
<identifier type="citekey">xu-etal-2024-generalization</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.424</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>7223</start>
<end>7243</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Generalization of Training-based ChatGPT Detection Methods
%A Xu, Han
%A Ren, Jie
%A He, Pengfei
%A Zeng, Shenglai
%A Cui, Yingqian
%A Liu, Amy
%A Liu, Hui
%A Tang, Jiliang
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F xu-etal-2024-generalization
%X Large language models, such as ChatGPT, achieve amazing performance on various language processing tasks. However, they can also be exploited for improper purposes such as plagiarism or misinformation dissemination. Thus, there is an urgent need to detect the texts generated by LLMs. One type of most studied methods trains classification models to distinguish LLM texts from human texts. However, existing studies demonstrate the trained models may suffer from distribution shifts (during test), i.e., they are ineffective to predict the generated texts from unseen language tasks or topics which are not collected during training. In this work, we focus on ChatGPT as a representative model, and we conduct a comprehensive investigation on these methods’ generalization behaviors under distribution shift caused by a wide range of factors, including prompts, text lengths, topics, and language tasks. To achieve this goal, we first collect a new dataset with human and ChatGPT texts, and then we conduct extensive studies on the collected dataset. Our studies unveil insightful findings that provide guidance for future methodologies and data collection strategies for LLM detection.
%U https://aclanthology.org/2024.findings-emnlp.424
%P 7223-7243
Markdown (Informal)
[On the Generalization of Training-based ChatGPT Detection Methods](https://aclanthology.org/2024.findings-emnlp.424) (Xu et al., Findings 2024)
ACL
- Han Xu, Jie Ren, Pengfei He, Shenglai Zeng, Yingqian Cui, Amy Liu, Hui Liu, and Jiliang Tang. 2024. On the Generalization of Training-based ChatGPT Detection Methods. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 7223–7243, Miami, Florida, USA. Association for Computational Linguistics.