SubmissionNumber#=%=#234 FinalPaperTitle#=%=#AILS-NTUA at SemEval-2024 Task 6: Efficient model tuning for hallucination detection and analysis ShortPaperTitle#=%=# NumberOfPages#=%=#12 CopyrightSigned#=%=#NATALIA GRIGORIADOU JobTitle#==#Student Organization#==#National Technical University of Athens, Heroon Polytechniou 9, 15780 Zografou, Greece Abstract#==#In this paper, we present our team's submissions for SemEval-2024 Task-6 - SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes. The participants were asked to perform binary classification to identify cases of fluent overgeneration hallucinations. Our experimentation included fine-tuning a pre-trained model on hallucination detection and a Natural Language Inference (NLI) model. The most successful strategy involved creating an ensemble of these models, resulting in accuracy rates of 77.8% and 79.9% on model-agnostic and model-aware datasets respectively, outperforming the organizers' baseline and achieving notable results when contrasted with the top-performing results in the competition, which reported accuracies of 84.7% and 81.3% correspondingly. Author{1}{Firstname}#=%=#Natalia Maria Author{1}{Lastname}#=%=#Grigoriadou Author{1}{Username}#=%=#natalygr Author{1}{Email}#=%=#natalygrigoriadi@gmail.com Author{1}{Affiliation}#=%=#National Technical University of Athens Author{2}{Firstname}#=%=#Maria Author{2}{Lastname}#=%=#Lymperaiou Author{2}{Username}#=%=#marialymperaiou Author{2}{Email}#=%=#marialymp@islab.ntua.gr Author{2}{Affiliation}#=%=#National Technical University of Athens Author{3}{Firstname}#=%=#George Author{3}{Lastname}#=%=#Filandrianos Author{3}{Username}#=%=#geofila Author{3}{Email}#=%=#geofila@islab.ntua.gr Author{3}{Affiliation}#=%=#National Technical University of Athens Author{4}{Firstname}#=%=#Giorgos Author{4}{Lastname}#=%=#Stamou Author{4}{Username}#=%=#gstam Author{4}{Email}#=%=#gstam@cs.ntua.gr Author{4}{Affiliation}#=%=#National Technical University of Athens ========== èéáğö