@inproceedings{yoo-etal-2024-exploring,
title = "Exploring Causal Mechanisms for Machine Text Detection Methods",
author = "Yoo, Kiyoon and
Ahn, Wonhyuk and
Song, Yeji and
Kwak, Nojun",
editor = "Ovalle, Anaelia and
Chang, Kai-Wei and
Cao, Yang Trista and
Mehrabi, Ninareh and
Zhao, Jieyu and
Galstyan, Aram and
Dhamala, Jwala and
Kumar, Anoop and
Gupta, Rahul",
booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.trustnlp-1.7",
doi = "10.18653/v1/2024.trustnlp-1.7",
pages = "71--78",
abstract = "The immense attraction towards text generation garnered by ChatGPT has spurred the need for discriminating machine-text from human text. In this work, we provide preliminary evidence that the scores computed by existing zero-shot and supervised machine-generated text detection methods are not solely determined by the generated texts, but are affected by prompts and real texts as well. Using techniques from causal inference, we show the existence of backdoor paths that confounds the relationships between text and its detection score and how the confounding bias can be partially mitigated. We open up new research directions in identifying other factors that may be interwoven in the detection of machine text. Our study calls for a deeper investigation into which kinds of prompts make the detection of machine text more difficult or easier",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yoo-etal-2024-exploring">
<titleInfo>
<title>Exploring Causal Mechanisms for Machine Text Detection Methods</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kiyoon</namePart>
<namePart type="family">Yoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wonhyuk</namePart>
<namePart type="family">Ahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yeji</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nojun</namePart>
<namePart type="family">Kwak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anaelia</namePart>
<namePart type="family">Ovalle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="given">Trista</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ninareh</namePart>
<namePart type="family">Mehrabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aram</namePart>
<namePart type="family">Galstyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jwala</namePart>
<namePart type="family">Dhamala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The immense attraction towards text generation garnered by ChatGPT has spurred the need for discriminating machine-text from human text. In this work, we provide preliminary evidence that the scores computed by existing zero-shot and supervised machine-generated text detection methods are not solely determined by the generated texts, but are affected by prompts and real texts as well. Using techniques from causal inference, we show the existence of backdoor paths that confounds the relationships between text and its detection score and how the confounding bias can be partially mitigated. We open up new research directions in identifying other factors that may be interwoven in the detection of machine text. Our study calls for a deeper investigation into which kinds of prompts make the detection of machine text more difficult or easier</abstract>
<identifier type="citekey">yoo-etal-2024-exploring</identifier>
<identifier type="doi">10.18653/v1/2024.trustnlp-1.7</identifier>
<location>
<url>https://aclanthology.org/2024.trustnlp-1.7</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>71</start>
<end>78</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Causal Mechanisms for Machine Text Detection Methods
%A Yoo, Kiyoon
%A Ahn, Wonhyuk
%A Song, Yeji
%A Kwak, Nojun
%Y Ovalle, Anaelia
%Y Chang, Kai-Wei
%Y Cao, Yang Trista
%Y Mehrabi, Ninareh
%Y Zhao, Jieyu
%Y Galstyan, Aram
%Y Dhamala, Jwala
%Y Kumar, Anoop
%Y Gupta, Rahul
%S Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F yoo-etal-2024-exploring
%X The immense attraction towards text generation garnered by ChatGPT has spurred the need for discriminating machine-text from human text. In this work, we provide preliminary evidence that the scores computed by existing zero-shot and supervised machine-generated text detection methods are not solely determined by the generated texts, but are affected by prompts and real texts as well. Using techniques from causal inference, we show the existence of backdoor paths that confounds the relationships between text and its detection score and how the confounding bias can be partially mitigated. We open up new research directions in identifying other factors that may be interwoven in the detection of machine text. Our study calls for a deeper investigation into which kinds of prompts make the detection of machine text more difficult or easier
%R 10.18653/v1/2024.trustnlp-1.7
%U https://aclanthology.org/2024.trustnlp-1.7
%U https://doi.org/10.18653/v1/2024.trustnlp-1.7
%P 71-78
Markdown (Informal)
[Exploring Causal Mechanisms for Machine Text Detection Methods](https://aclanthology.org/2024.trustnlp-1.7) (Yoo et al., TrustNLP-WS 2024)
ACL