@inproceedings{armannsson-etal-2025-icelandic,
    title = "An {Icelandic} Linguistic Benchmark for Large Language Models",
    author = "{\'A}rmannsson, Bjarki  and
      Ingimundarson, Finnur {\'A}g{\'u}st  and
      Sigur{\dh}sson, Einar Freyr",
    editor = "Johansson, Richard  and
      Stymne, Sara",
    booktitle = "Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)",
    month = mar,
    year = "2025",
    address = "Tallinn, Estonia",
    publisher = "University of Tartu Library",
    url = "https://preview.aclanthology.org/corrections-2025-06/2025.nodalida-1.5/",
    pages = "37--47",
    ISBN = "978-9908-53-109-0",
    abstract = "This paper introduces a linguistic benchmark for Icelandic-language LLMs, the first of its kind manually constructed by native speakers. We report on the scores obtained by current state-of-the-art models, which indicate room for improvement, and discuss the theoretical problems involved in creating such a benchmark and scoring a model{'}s performance."
}