@inproceedings{take-tran-2024-riddlemasters,
    title = "{R}iddle{M}asters at {S}em{E}val-2024 Task 9: Comparing Instruction Fine-tuning with Zero-Shot Approaches",
    author = "Take, Kejsi  and
      Tran, Chau",
    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_wac_2008/2024.semeval-1.200/",
    doi = "10.18653/v1/2024.semeval-1.200",
    pages = "1391--1396",
    abstract = "This paper describes our contribution to SemEval 2023 Task 8: Brainteaser. We compared multiple zero-shot approaches using GPT-4, the state of the art model with Mistral-7B, a much smaller open-source LLM. While GPT-4 remains a clear winner in all the zero-shot approaches, we show that finetuning Mistral-7B can achieve comparable, even though marginally lower results."
}