@inproceedings{van-oort-etal-2026-gpt,
    title = "{GPT}-{NL} Public Corpus: A Permissively Licensed, {D}utch-First Dataset for {LLM} Pre-training",
    author = "Van Oort, Jesse J.  and
      Brinkkemper, Frank  and
      de Graaf, Erik  and
      Vanroy, Bram  and
      Lensink, Saskia",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-1.548/",
    doi = "10.63317/5fbtc336wwx2",
    pages = "6893--6903"
}