@inproceedings{samuel-etal-2025-small,
    title = "Small Languages, Big Models: {A} Study of Continual Training on Languages of {Norway}",
    author = "Samuel, David  and
      Mikhailov, Vladislav  and
      Velldal, Erik  and
      {\O}vrelid, Lilja  and
      Charpentier, Lucas Georges Gabriel  and
      Kutuzov, Andrey  and
      Oepen, Stephan",
    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/fix-sig-urls/2025.nodalida-1.61/",
    pages = "573--608",
    ISBN = "978-9908-53-109-0",
    abstract = "Training large language models requires vast amounts of data, posing a challenge for less widely spoken languages like Norwegian and even more so for truly low-resource languages like Northern S{\'a}mi. To address this issue, we present a novel three-stage continual training approach that substantially improves the downstream performance together with the inference efficiency for the target languages. Based on our findings, we train, evaluate, and openly release a new generative language model for Norwegian Bokm{\r{a}}l, Nynorsk, and Northern S{\'a}mi with 11.4 billion parameters: NorMistral-11B."
}