@article{veerbeek-etal-2026-memorization,
    title = "Memorization or Lucky Guesses: Detecting Short Sequences from Copyrighted {D}utch News in {LLM} Output",
    author = "Veerbeek, Joris  and
      Berendsen, Kas  and
      Polimeno, Alessandra  and
      van den Bosch, Antal",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.473/",
    pages = "5960--5969",
    abstract = "Demonstrating that large language models have memorized copyrighted material is more feasible for high-volume publishers than for smaller outlets whose content appears less frequently online. This study explores how even short, repeated sequences{--}rather than full articles{--}can serve as evidence of memorization. Focusing on Dutch news sources included in the mC4 dataset, we test whether GPT-4 and mT5 reproduce excerpts from thousands of articles, including standardized editorial boilerplate. By comparing results to a post-training baseline and modeling memorization as a survival process, we find that repeated, publication-specific phrases are significantly more likely to be completed verbatim. The approach provides a means to detect empirical evidence of memorization in cases where full reproduction is unlikely."
}