@inproceedings{petukhova-etal-2024-petkaz,
    title = "{P}et{K}az at {S}em{E}val-2024 Task 8: Can Linguistics Capture the Specifics of {LLM}-generated Text?",
    author = "Petukhova, Kseniia  and
      Kazakov, Roman  and
      Kochmar, Ekaterina",
    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/jlcl-multiple-ingestion/2024.semeval-1.166/",
    doi = "10.18653/v1/2024.semeval-1.166",
    pages = "1140--1147",
    abstract = "In this paper, we present our submission to the SemEval-2024 Task 8 {\textquotedblleft}Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection{\textquotedblright}, focusing on the detection of machine-generated texts (MGTs) in English. Specifically, our approach relies on combining embeddings from the RoBERTa-base with diversity features and uses a resampled training set. We score 16th from 139 in the ranking for Subtask A, and our results show that our approach is generalizable across unseen models and domains, achieving an accuracy of 0.91."
}