@inproceedings{chen-etal-2024-team,
    title = "Team {MGTD}4{ADL} at {S}em{E}val-2024 Task 8: Leveraging (Sentence) Transformer Models with Contrastive Learning for Identifying Machine-Generated Text",
    author = {Chen, Huixin  and
      B{\"u}ssing, Jan  and
      R{\"u}gamer, David  and
      Nie, Ercong},
    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://preview.aclanthology.org/add-emnlp-2024-awards/2024.semeval-1.245/",
    doi = "10.18653/v1/2024.semeval-1.245",
    pages = "1711--1718",
    abstract = "This paper outlines our approach to SemEval-2024 Task 8 (Subtask B), which focuses on discerning machine-generated text from human-written content, while also identifying the text sources, i.e., from which Large Language Model (LLM) the target text is generated. Our detection system is built upon Transformer-based techniques, leveraging various pre-trained language models (PLMs), including sentence transformer models. Additionally, we incorporate Contrastive Learning (CL) into the classifier to improve the detecting capabilities and employ Data Augmentation methods. Ultimately, our system achieves a peak accuracy of 76.96{\%} on the test set of the competition, configured using a sentence transformer model integrated with CL methodology."
}