@inproceedings{siino-2024-badrock,
title = "{B}ad{R}ock at {S}em{E}val-2024 Task 8: {D}istil{BERT} to Detect Multigenerator, Multidomain and Multilingual Black-Box Machine-Generated Text",
author = "Siino, Marco",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Tayyar Madabushi, Harish and
Da San Martino, Giovanni and
Rosenthal, Sara and
Ros{\'a}, Aiala},
booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.semeval-1.37",
pages = "239--245",
abstract = "The rise of Large Language Models (LLMs) has brought about a notable shift, rendering them increasingly ubiquitous and readily accessible. This accessibility has precipitated a surge in machine-generated content across diverse platforms encompassing news outlets, social media platforms, question-answering forums, educational platforms, and even academic domains. Recent iterations of LLMs, exemplified by entities like ChatGPT and GPT-4, exhibit a remarkable ability to produce coherent and contextually relevant responses across a broad spectrum of user inquiries. The fluidity and sophistication of these generated texts position LLMs as compelling candidates for substituting human labor in numerous applications. Nevertheless, this proliferation of machine-generated content has raised apprehensions regarding potential misuse, including the dissemination of misinformation and disruption of educational ecosystems. Given that humans marginally outperform random chance in discerning between machine-generated and human-authored text, there arises a pressing imperative to develop automated systems capable of accurately distinguishing machine-generated text. This pursuit is driven by the overarching objective of curbing the potential misuse of machine-generated content. Our manuscript delineates the approach we adopted for participation in this competition. Specifically, we detail the use of a DistilBERT model for classifying each sample in the test set provided. Our submission is able to reach an accuracy equal to 0.754 in place of the worst result obtained at the competition that is equal to 0.231.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="siino-2024-badrock">
<titleInfo>
<title>BadRock at SemEval-2024 Task 8: DistilBERT to Detect Multigenerator, Multidomain and Multilingual Black-Box Machine-Generated Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Siino</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 18th International Workshop on Semantic Evaluation (SemEval-2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</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 rise of Large Language Models (LLMs) has brought about a notable shift, rendering them increasingly ubiquitous and readily accessible. This accessibility has precipitated a surge in machine-generated content across diverse platforms encompassing news outlets, social media platforms, question-answering forums, educational platforms, and even academic domains. Recent iterations of LLMs, exemplified by entities like ChatGPT and GPT-4, exhibit a remarkable ability to produce coherent and contextually relevant responses across a broad spectrum of user inquiries. The fluidity and sophistication of these generated texts position LLMs as compelling candidates for substituting human labor in numerous applications. Nevertheless, this proliferation of machine-generated content has raised apprehensions regarding potential misuse, including the dissemination of misinformation and disruption of educational ecosystems. Given that humans marginally outperform random chance in discerning between machine-generated and human-authored text, there arises a pressing imperative to develop automated systems capable of accurately distinguishing machine-generated text. This pursuit is driven by the overarching objective of curbing the potential misuse of machine-generated content. Our manuscript delineates the approach we adopted for participation in this competition. Specifically, we detail the use of a DistilBERT model for classifying each sample in the test set provided. Our submission is able to reach an accuracy equal to 0.754 in place of the worst result obtained at the competition that is equal to 0.231.</abstract>
<identifier type="citekey">siino-2024-badrock</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.37</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>239</start>
<end>245</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BadRock at SemEval-2024 Task 8: DistilBERT to Detect Multigenerator, Multidomain and Multilingual Black-Box Machine-Generated Text
%A Siino, Marco
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Tayyar Madabushi, Harish
%Y Da San Martino, Giovanni
%Y Rosenthal, Sara
%Y Rosá, Aiala
%S Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F siino-2024-badrock
%X The rise of Large Language Models (LLMs) has brought about a notable shift, rendering them increasingly ubiquitous and readily accessible. This accessibility has precipitated a surge in machine-generated content across diverse platforms encompassing news outlets, social media platforms, question-answering forums, educational platforms, and even academic domains. Recent iterations of LLMs, exemplified by entities like ChatGPT and GPT-4, exhibit a remarkable ability to produce coherent and contextually relevant responses across a broad spectrum of user inquiries. The fluidity and sophistication of these generated texts position LLMs as compelling candidates for substituting human labor in numerous applications. Nevertheless, this proliferation of machine-generated content has raised apprehensions regarding potential misuse, including the dissemination of misinformation and disruption of educational ecosystems. Given that humans marginally outperform random chance in discerning between machine-generated and human-authored text, there arises a pressing imperative to develop automated systems capable of accurately distinguishing machine-generated text. This pursuit is driven by the overarching objective of curbing the potential misuse of machine-generated content. Our manuscript delineates the approach we adopted for participation in this competition. Specifically, we detail the use of a DistilBERT model for classifying each sample in the test set provided. Our submission is able to reach an accuracy equal to 0.754 in place of the worst result obtained at the competition that is equal to 0.231.
%U https://aclanthology.org/2024.semeval-1.37
%P 239-245
Markdown (Informal)
[BadRock at SemEval-2024 Task 8: DistilBERT to Detect Multigenerator, Multidomain and Multilingual Black-Box Machine-Generated Text](https://aclanthology.org/2024.semeval-1.37) (Siino, SemEval 2024)
ACL