@inproceedings{iordanidou-etal-2024-duth,
    title = "{DUT}h at {S}em{E}val-2024 Task 6: Comparing Pre-trained Models on Sentence Similarity Evaluation for Detecting of Hallucinations and Related Observable Overgeneration Mistakes",
    author = "Iordanidou, Ioanna  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/jlcl-multiple-ingestion/2024.semeval-1.154/",
    doi = "10.18653/v1/2024.semeval-1.154",
    pages = "1064--1070",
    abstract = "In this paper, we present our approach toSemEval-2024 Task 6: SHROOM, a Sharedtask on Hallucinations and Related ObservableOvergeneration Mistakes, which aims to determine weather AI generated text is semanticallycorrect or incorrect. This work is a comparative study of Large Language Models (LLMs)in the context of the task, shedding light ontheir effectiveness and nuances. We present asystem that leverages pre-trained LLMs, suchas LaBSE, T5, and DistilUSE, for binary classification of given sentences into {\textquoteleft}Hallucination`or {\textquoteleft}Not Hallucination' classes by evaluatingthe model`s output against the reference correct text. Moreover, beyond utilizing labeleddatasets, our methodology integrates syntheticlabel creation in unlabeled datasets, followedby the prediction of test labels."
}