@inproceedings{rosa-etal-2025-impact,
    title = "The Impact of Copyrighted Material on Large Language Models: {A} {Norwegian} Perspective",
    author = "de la Rosa, Javier  and
      Mikhailov, Vladislav  and
      Zhang, Lemei  and
      Wetjen, Freddy  and
      Samuel, David  and
      Liu, Peng  and
      Braaten, Rolv-Arild  and
      M{\ae}hlum, Petter  and
      Birkenes, Magnus Breder  and
      Kutuzov, Andrey  and
      Enstad, Tita  and
      Farseth{\r{a}}s, Hans Christian  and
      Brygfjeld, Svein Arne  and
      Gulla, Jon Atle  and
      Oepen, Stephan  and
      Velldal, Erik  and
      {\O}stgulen, Wilfred  and
      {\O}vrelid, Lilja  and
      Myhre, Aslak Sira",
    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-1.59/",
    pages = "544--560",
    ISBN = "978-9908-53-109-0",
    abstract = "The use of copyrighted materials in training language models raises critical legal and ethical questions. This paper presents a framework for and the results of empirically assessing the impact of publisher-controlled copyrighted corpora on the performance of generative large language models (LLMs) for Norwegian. When evaluated on a diverse set of tasks, we found that adding both books and newspapers to the data mixture of LLMs tend to improve their performance, while the addition of fiction works seems to be detrimental. Our experiments could inform the creation of a compensation scheme for authors whose works contribute to AI development."
}