@inproceedings{peixoto-etal-2026-global,
    title = "Global vs. Local Sentence Embeddings for {B}razilian {P}ortuguese: Revisiting Monolingual Models in the Age of Foundation Models",
    author = "Peixoto, Matheus  and
      Silva, Guilherme  and
      Figueredo, Giacomo  and
      Silva, Pedro  and
      Luz, Eduardo J. S.",
    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-1.52/",
    pages = "529--539",
    ISBN = "979-8-89176-387-6",
    abstract = "The choice between large-scale, multilingual, foundation models and specialized monolingual models for languages like Brazilian Portuguese (PT-BR) presents a complex trade-off between generalization and specialization. This paper investigates this trade-off through an empirical study across a diverse suite of tasks. We evaluate multiple families of language models under both linear probing and fine-tuning regimes. We find that monolingual encoders exhibit greater ``adaptation plasticity'' during fine-tuning, improving on both classification and semantic similarity, where global (multilingual) models degrade. However, this plasticity comes at a cost: our tokenization analysis suggests that monolingual models struggle with foreign terms, whereas modern multilingual tokenizers show surprising morphological competence, challenging a long-standing assumption in the field. We conclude that the optimal model choice is a task-dependent trade-off between vocabulary coverage and adaptation flexibility."
}