@inproceedings{joy-aishi-2023-feature,
title = "Feature-Level Ensemble Learning for Robust Synthetic Text Detection with {D}e{BERT}a{V}3 and {XLM}-{R}o{BERT}a",
author = "Joy, Saman Sarker and
Aishi, Tanusree Das",
editor = "Muresan, Smaranda and
Chen, Vivian and
Casey, Kennington and
David, Vandyke and
Nina, Dethlefs and
Koji, Inoue and
Erik, Ekstedt and
Stefan, Ultes",
booktitle = "Proceedings of the 21st Annual Workshop of the Australasian Language Technology Association",
month = nov,
year = "2023",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.alta-1.21",
pages = "169--172",
abstract = "As large language models, or LLMs, continue to advance in recent years, they require the development of a potent system to detect whether a text was created by a human or an LLM in order to prevent the unethical use of LLMs. To address this challenge, ALTA Shared Task 2023 introduced a task to build an automatic detection system that can discriminate between human-authored and synthetic text generated by LLMs. In this paper, we present our participation in this task where we proposed a feature-level ensemble of two transformer models namely DeBERTaV3 and XLM-RoBERTa to come up with a robust system. The given dataset consisted of textual data with two labels where the task was binary classification. Experimental results show that our proposed method achieved competitive performance among the participants. We believe this solution would make an impact and provide a feasible solution for detection of synthetic text detection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="joy-aishi-2023-feature">
<titleInfo>
<title>Feature-Level Ensemble Learning for Robust Synthetic Text Detection with DeBERTaV3 and XLM-RoBERTa</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saman</namePart>
<namePart type="given">Sarker</namePart>
<namePart type="family">Joy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanusree</namePart>
<namePart type="given">Das</namePart>
<namePart type="family">Aishi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st Annual Workshop of the Australasian Language Technology Association</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivian</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kennington</namePart>
<namePart type="family">Casey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vandyke</namePart>
<namePart type="family">David</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dethlefs</namePart>
<namePart type="family">Nina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inoue</namePart>
<namePart type="family">Koji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekstedt</namePart>
<namePart type="family">Erik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ultes</namePart>
<namePart type="family">Stefan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As large language models, or LLMs, continue to advance in recent years, they require the development of a potent system to detect whether a text was created by a human or an LLM in order to prevent the unethical use of LLMs. To address this challenge, ALTA Shared Task 2023 introduced a task to build an automatic detection system that can discriminate between human-authored and synthetic text generated by LLMs. In this paper, we present our participation in this task where we proposed a feature-level ensemble of two transformer models namely DeBERTaV3 and XLM-RoBERTa to come up with a robust system. The given dataset consisted of textual data with two labels where the task was binary classification. Experimental results show that our proposed method achieved competitive performance among the participants. We believe this solution would make an impact and provide a feasible solution for detection of synthetic text detection.</abstract>
<identifier type="citekey">joy-aishi-2023-feature</identifier>
<location>
<url>https://aclanthology.org/2023.alta-1.21</url>
</location>
<part>
<date>2023-11</date>
<extent unit="page">
<start>169</start>
<end>172</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Feature-Level Ensemble Learning for Robust Synthetic Text Detection with DeBERTaV3 and XLM-RoBERTa
%A Joy, Saman Sarker
%A Aishi, Tanusree Das
%Y Muresan, Smaranda
%Y Chen, Vivian
%Y Casey, Kennington
%Y David, Vandyke
%Y Nina, Dethlefs
%Y Koji, Inoue
%Y Erik, Ekstedt
%Y Stefan, Ultes
%S Proceedings of the 21st Annual Workshop of the Australasian Language Technology Association
%D 2023
%8 November
%I Association for Computational Linguistics
%C Melbourne, Australia
%F joy-aishi-2023-feature
%X As large language models, or LLMs, continue to advance in recent years, they require the development of a potent system to detect whether a text was created by a human or an LLM in order to prevent the unethical use of LLMs. To address this challenge, ALTA Shared Task 2023 introduced a task to build an automatic detection system that can discriminate between human-authored and synthetic text generated by LLMs. In this paper, we present our participation in this task where we proposed a feature-level ensemble of two transformer models namely DeBERTaV3 and XLM-RoBERTa to come up with a robust system. The given dataset consisted of textual data with two labels where the task was binary classification. Experimental results show that our proposed method achieved competitive performance among the participants. We believe this solution would make an impact and provide a feasible solution for detection of synthetic text detection.
%U https://aclanthology.org/2023.alta-1.21
%P 169-172
Markdown (Informal)
[Feature-Level Ensemble Learning for Robust Synthetic Text Detection with DeBERTaV3 and XLM-RoBERTa](https://aclanthology.org/2023.alta-1.21) (Joy & Aishi, ALTA 2023)
ACL