@inproceedings{brekhof-etal-2024-groningen,
title = "{G}roningen team {D} at {S}em{E}val-2024 Task 8: Exploring data generation and a combined model for fine-tuning {LLM}s for Multidomain Machine-Generated Text Detection",
author = "Brekhof, Thijs and
Liu, Xuanyi and
Ruitenbeek, Joris and
Top, Niels and
Zhou, Yuwen",
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-1.61/",
doi = "10.18653/v1/2024.semeval-1.61",
pages = "391--398",
abstract = "In this system description, we describe our process and the systems that we created for the subtasks A monolingual, A multilingual, and B forthe SemEval-2024 Task 8: Multigenerator, Multidomain, and Multilingual Black-Box MachineGenerated Text Detection. This shared task aimsat detecting and differentiating between machinegenerated text and human-written text. SubtaskA is focused on detecting if a text is machinegenerated or human-written both in a monolingualand a multilingual setting. Subtask B is also focused on detecting if a text is human-written ormachine-generated, though it takes it one step further by also requiring the detection of the correct language model used for generating the text.For the monolingual aspects of this task, our approach is centered around fine-tuning a debertav3-large LM. For the multilingual setting, we created an ensemble model utilizing different monolingual models and a language identification toolto classify each text. We also experiment with thegeneration of extra training data. Our results showthat the generation of extra data aids our modelsand leads to an increase in accuracy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brekhof-etal-2024-groningen">
<titleInfo>
<title>Groningen team D at SemEval-2024 Task 8: Exploring data generation and a combined model for fine-tuning LLMs for Multidomain Machine-Generated Text Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thijs</namePart>
<namePart type="family">Brekhof</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanyi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joris</namePart>
<namePart type="family">Ruitenbeek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niels</namePart>
<namePart type="family">Top</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuwen</namePart>
<namePart type="family">Zhou</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>In this system description, we describe our process and the systems that we created for the subtasks A monolingual, A multilingual, and B forthe SemEval-2024 Task 8: Multigenerator, Multidomain, and Multilingual Black-Box MachineGenerated Text Detection. This shared task aimsat detecting and differentiating between machinegenerated text and human-written text. SubtaskA is focused on detecting if a text is machinegenerated or human-written both in a monolingualand a multilingual setting. Subtask B is also focused on detecting if a text is human-written ormachine-generated, though it takes it one step further by also requiring the detection of the correct language model used for generating the text.For the monolingual aspects of this task, our approach is centered around fine-tuning a debertav3-large LM. For the multilingual setting, we created an ensemble model utilizing different monolingual models and a language identification toolto classify each text. We also experiment with thegeneration of extra training data. Our results showthat the generation of extra data aids our modelsand leads to an increase in accuracy.</abstract>
<identifier type="citekey">brekhof-etal-2024-groningen</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.61</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.61/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>391</start>
<end>398</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Groningen team D at SemEval-2024 Task 8: Exploring data generation and a combined model for fine-tuning LLMs for Multidomain Machine-Generated Text Detection
%A Brekhof, Thijs
%A Liu, Xuanyi
%A Ruitenbeek, Joris
%A Top, Niels
%A Zhou, Yuwen
%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 brekhof-etal-2024-groningen
%X In this system description, we describe our process and the systems that we created for the subtasks A monolingual, A multilingual, and B forthe SemEval-2024 Task 8: Multigenerator, Multidomain, and Multilingual Black-Box MachineGenerated Text Detection. This shared task aimsat detecting and differentiating between machinegenerated text and human-written text. SubtaskA is focused on detecting if a text is machinegenerated or human-written both in a monolingualand a multilingual setting. Subtask B is also focused on detecting if a text is human-written ormachine-generated, though it takes it one step further by also requiring the detection of the correct language model used for generating the text.For the monolingual aspects of this task, our approach is centered around fine-tuning a debertav3-large LM. For the multilingual setting, we created an ensemble model utilizing different monolingual models and a language identification toolto classify each text. We also experiment with thegeneration of extra training data. Our results showthat the generation of extra data aids our modelsand leads to an increase in accuracy.
%R 10.18653/v1/2024.semeval-1.61
%U https://aclanthology.org/2024.semeval-1.61/
%U https://doi.org/10.18653/v1/2024.semeval-1.61
%P 391-398
Markdown (Informal)
[Groningen team D at SemEval-2024 Task 8: Exploring data generation and a combined model for fine-tuning LLMs for Multidomain Machine-Generated Text Detection](https://aclanthology.org/2024.semeval-1.61/) (Brekhof et al., SemEval 2024)
ACL