@inproceedings{marchitan-etal-2024-team,
    title = "Team {U}nibuc - {NLP} at {S}em{E}val-2024 Task 8: Transformer and Hybrid Deep Learning Based Models for Machine-Generated Text Detection",
    author = "Marchitan, Teodor-george  and
      Creanga, Claudiu  and
      Dinu, Liviu P.",
    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/fix-sig-urls/2024.semeval-1.63/",
    doi = "10.18653/v1/2024.semeval-1.63",
    pages = "403--411",
    abstract = "This paper describes the approach of the UniBuc - NLP team in tackling the SemEval 2024 Task 8: Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection. We explored transformer-based and hybrid deep learning architectures. For subtask B, our transformer-based model achieved a strong second-place out of 77 teams with an accuracy of 86.95{\%}, demonstrating the architecture{'}s suitability for this task. However, our models showed overfitting in subtask A which could potentially be fixed with less fine-tunning and increasing maximum sequence length. For subtask C (token-level classification), our hybrid model overfit during training, hindering its ability to detect transitions between human and machine-generated text."
}