HU at SemEval-2024 Task 8A: Can Contrastive Learning Learn Embeddings to Detect Machine-Generated Text?

Shubhashis Roy Dipta, Sadat Shahriar


Abstract
This paper describes our system developed for SemEval-2024 Task 8, “Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection.” Machine-generated texts have been one of the main concerns due to the use of large language models (LLM) in fake text generation, phishing, cheating in exams, or even plagiarizing copyright materials. A lot of systems have been developed to detect machine-generated text. Nonetheless, the majority of these systems rely on the text-generating model. This limitation is impractical in real-world scenarios, as it’s often impossible to know which specific model the user has used for text generation. In this work, we propose a single model based on contrastive learning, which uses ~40% of the baseline’s parameters (149M vs. 355M) but shows a comparable performance on the test dataset (21st out of 137 participants). Our key finding is that even without an ensemble of multiple models, a single base model can have comparable performance with the help of data augmentation and contrastive learning.
Anthology ID:
2024.semeval-1.74
Volume:
Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Atul Kr. Ojha, A. Seza Doğruöz, Harish Tayyar Madabushi, Giovanni Da San Martino, Sara Rosenthal, Aiala Rosá
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
485–491
Language:
URL:
https://aclanthology.org/2024.semeval-1.74
DOI:
10.18653/v1/2024.semeval-1.74
Bibkey:
Cite (ACL):
Shubhashis Roy Dipta and Sadat Shahriar. 2024. HU at SemEval-2024 Task 8A: Can Contrastive Learning Learn Embeddings to Detect Machine-Generated Text?. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 485–491, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
HU at SemEval-2024 Task 8A: Can Contrastive Learning Learn Embeddings to Detect Machine-Generated Text? (Roy Dipta & Shahriar, SemEval 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.semeval-1.74.pdf
Supplementary material:
 2024.semeval-1.74.SupplementaryMaterial.txt
Supplementary material:
 2024.semeval-1.74.SupplementaryMaterial.zip