@inproceedings{touileb-etal-2025-benchmarking,
    title = "Benchmarking Abstractive Summarisation: {A} Dataset of Human-authored Summaries of {Norwegian} News Articles",
    author = "Touileb, Samia  and
      Mikhailov, Vladislav  and
      Kroka, Marie Ingeborg  and
      {\O}vrelid, Lilja  and
      Velldal, Erik",
    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-1.73/",
    pages = "729--738",
    ISBN = "978-9908-53-109-0",
    abstract = "We introduce a dataset of high-quality human-authored summaries of news articles in Norwegian. The dataset is intended for benchmarking of the abstractive summarisation capabilities of generative language models. Each document in the dataset is provided with three different candidate gold-standard summaries written by native Norwegian speakers and all summaries are provided in both of the written variants of Norwegian {--} Bokm{\r{a}}l and Nynorsk. The paper describes details on the data creation effort as well as an evaluation of existing open LLMs for Norwegian on the dataset. We also provide insights from a manual human evaluation, comparing human-authored to model generated summaries. Our results indicate that the dataset provides a challenging LLM benchmark for Norwegian summarisation capabilities."
}