@inproceedings{krasnodebska-etal-2025-pl,
    title = "{PL}-Guard: Benchmarking Language Model Safety for {P}olish",
    author = "Krasnodebska, Aleksandra  and
      Seweryn, Karolina  and
      {\L}ukasik, Szymon  and
      Kusa, Wojciech",
    editor = "Piskorski, Jakub  and
      P{\v{r}}ib{\'a}{\v{n}}, Pavel  and
      Nakov, Preslav  and
      Yangarber, Roman  and
      Marcinczuk, Michal",
    booktitle = "Proceedings of the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.bsnlp-1.4/",
    pages = "25--37",
    ISBN = "978-1-959429-57-9",
    abstract = "We present a benchmark dataset for evaluating language model safety in Polish, addressing the underrepresentation of medium-resource languages in existing safety assessments. Our dataset includes both original and adversarially perturbed examples. We fine-tune and evaluate multiple models{---}LlamaGuard-3-8B, a HerBERT-based classifier, and PLLuM{---}and find that the HerBERT-based model outperforms others, especially under adversarial conditions."
}