@inproceedings{sousa-etal-2026-curupira,
    title = "{CURUPIRA}: Clever guard for harm and linguistic prompt mitigation in {B}razilian {P}ortuguese",
    author = "Sousa, Rog{\'e}rio  and
      Cruz-Casta{\~n}eda, William Alberto  and
      Silva, Jos{\'e} Roberto Homeli  and
      Amadeus, Marcellus",
    editor = "Souza, Marlo  and
      de-Dios-Flores, Iria  and
      Santos, Diana  and
      Freitas, Larissa  and
      Souza, Jackson Wilke da Cruz  and
      Ribeiro, Eug{\'e}nio",
    booktitle = "Proceedings of the 17th International Conference on Computational Processing of {P}ortuguese ({PROPOR} 2026) - Vol. 1",
    month = apr,
    year = "2026",
    address = "Salvador, Brazil",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-dnd/2026.propor-1.107/",
    pages = "1038--1043",
    ISBN = "979-8-89176-387-6",
    abstract = "The safe deployment of Large Language Models remains challenging in multilingual settings, particularly when models are exposed to adversarial or malicious prompts in underrepresented languages. In this work, we present Curupira, a Brazilian Portuguese-language guard model designed to mitigate harmful prompt exploitation. To do this, we establish a three steps methodology that involves adaptation, data generation, and fine-tuning. We also evaluate our model with two state-of-the-art open guardrail architectures. The results show that targeted fine-tuning leads to consistent improvements in safety classification for Portuguese prompts, with favorable efficiency{--}performance trade-offs for compact models and limited degradation in cross-lingual evaluation."
}