@inproceedings{simoes-etal-2026-field,
    title = "Field of Science and Technology Classification of Academic Documents in {P}ortuguese",
    author = "Sim{\~o}es, Ivo  and
      Oliveira, Hugo Gon{\c{c}}alo  and
      Correia, Jo{\~a}o",
    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-1.104/",
    pages = "1021--1026",
    ISBN = "979-8-89176-387-6",
    abstract = "Towards improving metadata in academic repositories, this study evaluates the efficacy of different transformer-based models in the automatic classification of the Field of Science and Technology (FOS) of academic theses written in Portuguese. We compare the performance of four different encoder models, two multilingual and two Portuguese-specific, against five larger decoder-based LLMs, on a dataset of 9,696 theses characterized by their title, keywords, and abstract. Fine-tuned encoder-based models achieved the best scores (F1 = 88{\%}), outperforming general-purpose decoder models prompted for the task. These results suggest that, for localized academic domains, task-specific fine-tuning remains more effective than general-purpose LLM prompting."
}