@inproceedings{kyriakou-etal-2024-duth,
    title = "{DUT}h at {S}em{E}val 2024 Task 8: Comparing classic Machine Learning Algorithms and {LLM} based methods for Multigenerator, Multidomain and Multilingual Machine-Generated Text Detection",
    author = "Kyriakou, Theodora  and
      Maslaris, Ioannis  and
      Arampatzis, Avi",
    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/Ingest-2025-COMPUTEL/2024.semeval-1.156/",
    doi = "10.18653/v1/2024.semeval-1.156",
    pages = "1080--1086",
    abstract = "Text-generative models evolve rapidly nowadays. Although, they are very useful tools for a lot of people, they have also raised concerns for different reasons. This paper presents our work for SemEval2024 Task-8 on 2 out of the 3 subtasks. This shared task aims at finding automatic models for making AI vs. human written text classification easier. Our team, after trying different preprocessing, several Machine Learning algorithms, and some LLMs, ended up with mBERT, XLM-RoBERTa, and BERT for the tasks we submitted. We present both positive and negative methods, so that future researchers are informed about what works and what doesn`t."
}