@inproceedings{farokh-zeinali-2024-alf,
    title = "{ALF} at {S}em{E}val-2024 Task 9: Exploring Lateral Thinking Capabilities of {LM}s through Multi-task Fine-tuning",
    author = "Farokh, Seyed Ali  and
      Zeinali, Hossein",
    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-1.218/",
    doi = "10.18653/v1/2024.semeval-1.218",
    pages = "1523--1528",
    abstract = "Recent advancements in natural language processing (NLP) have prompted the development of sophisticated reasoning benchmarks. This paper presents our system for the SemEval 2024 Task 9 competition and also investigates the efficacy of fine-tuning language models (LMs) on BrainTeaser{---}a benchmark designed to evaluate NLP models' lateral thinking and creative reasoning abilities. Our experiments focus on two prominent families of pre-trained models, BERT and T5. Additionally, we explore the potential benefits of multi-task fine-tuning on commonsense reasoning datasets to enhance performance. Our top-performing model, DeBERTa-v3-large, achieves an impressive overall accuracy of 93.33{\%}, surpassing human performance."
}