@inproceedings{li-etal-2024-team,
title = "Team {ML}ab at {S}em{E}val-2024 Task 8: Analyzing Encoder Embeddings for Detecting {LLM}-generated Text",
author = "Li, Kevin and
Hasanaliyev, Kenan and
Zhu, Sally and
Altshuler, George and
Eberts, Alden and
Chen, Eric and
Wang, Kate and
Xia, Emily and
Browne, Eli and
Chen, Ian",
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-1.210",
doi = "10.18653/v1/2024.semeval-1.210",
pages = "1463--1467",
abstract = "This paper explores solutions to the challenges posed by the widespread use of LLMs, particularly in the context of identifying human-written versus machine-generated text. Focusing on Subtask B of SemEval 2024 Task 8, we compare the performance of RoBERTa and DeBERTa models. Subtask B involved identifying not only human or machine text but also the specific LLM responsible for generating text, where our DeBERTa model outperformed the RoBERTa baseline by over 10{\%} in leaderboard accuracy. The results highlight the rapidly growing capabilities of LLMs and importance of keeping up with the latest advancements. Additionally, our paper presents visualizations using PCA and t-SNE that showcase the DeBERTa model{'}s ability to cluster different LLM outputs effectively. These findings contribute to understanding and improving AI methods for detecting machine-generated text, allowing us to build more robust and traceable AI systems in the language ecosystem.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-team">
<titleInfo>
<title>Team MLab at SemEval-2024 Task 8: Analyzing Encoder Embeddings for Detecting LLM-generated Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenan</namePart>
<namePart type="family">Hasanaliyev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sally</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Altshuler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alden</namePart>
<namePart type="family">Eberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kate</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eli</namePart>
<namePart type="family">Browne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ian</namePart>
<namePart type="family">Chen</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>This paper explores solutions to the challenges posed by the widespread use of LLMs, particularly in the context of identifying human-written versus machine-generated text. Focusing on Subtask B of SemEval 2024 Task 8, we compare the performance of RoBERTa and DeBERTa models. Subtask B involved identifying not only human or machine text but also the specific LLM responsible for generating text, where our DeBERTa model outperformed the RoBERTa baseline by over 10% in leaderboard accuracy. The results highlight the rapidly growing capabilities of LLMs and importance of keeping up with the latest advancements. Additionally, our paper presents visualizations using PCA and t-SNE that showcase the DeBERTa model’s ability to cluster different LLM outputs effectively. These findings contribute to understanding and improving AI methods for detecting machine-generated text, allowing us to build more robust and traceable AI systems in the language ecosystem.</abstract>
<identifier type="citekey">li-etal-2024-team</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.210</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.210</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1463</start>
<end>1467</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Team MLab at SemEval-2024 Task 8: Analyzing Encoder Embeddings for Detecting LLM-generated Text
%A Li, Kevin
%A Hasanaliyev, Kenan
%A Zhu, Sally
%A Altshuler, George
%A Eberts, Alden
%A Chen, Eric
%A Wang, Kate
%A Xia, Emily
%A Browne, Eli
%A Chen, Ian
%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 li-etal-2024-team
%X This paper explores solutions to the challenges posed by the widespread use of LLMs, particularly in the context of identifying human-written versus machine-generated text. Focusing on Subtask B of SemEval 2024 Task 8, we compare the performance of RoBERTa and DeBERTa models. Subtask B involved identifying not only human or machine text but also the specific LLM responsible for generating text, where our DeBERTa model outperformed the RoBERTa baseline by over 10% in leaderboard accuracy. The results highlight the rapidly growing capabilities of LLMs and importance of keeping up with the latest advancements. Additionally, our paper presents visualizations using PCA and t-SNE that showcase the DeBERTa model’s ability to cluster different LLM outputs effectively. These findings contribute to understanding and improving AI methods for detecting machine-generated text, allowing us to build more robust and traceable AI systems in the language ecosystem.
%R 10.18653/v1/2024.semeval-1.210
%U https://aclanthology.org/2024.semeval-1.210
%U https://doi.org/10.18653/v1/2024.semeval-1.210
%P 1463-1467
Markdown (Informal)
[Team MLab at SemEval-2024 Task 8: Analyzing Encoder Embeddings for Detecting LLM-generated Text](https://aclanthology.org/2024.semeval-1.210) (Li et al., SemEval 2024)
ACL
- Kevin Li, Kenan Hasanaliyev, Sally Zhu, George Altshuler, Alden Eberts, Eric Chen, Kate Wang, Emily Xia, Eli Browne, and Ian Chen. 2024. Team MLab at SemEval-2024 Task 8: Analyzing Encoder Embeddings for Detecting LLM-generated Text. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 1463–1467, Mexico City, Mexico. Association for Computational Linguistics.