@inproceedings{junqueira-etal-2026-lari,
    title = "{LARI} Dataset: A Native {P}ortuguese Question Answering Dataset from Brasileiras em {PLN}",
    author = "Junqueira, J{\'u}lia da Rocha  and
      Freitas, Larissa A. de  and
      Corr{\^e}a, Ulisses Brisolara",
    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-1.110/",
    pages = "1055--1061",
    ISBN = "979-8-89176-387-6",
    abstract = "Recent advances in the field have revolutionized Question and Answering (QA). However, for languages like Portuguese, progress is often hindered by the lack of native training resources. To address this gap, this paper introduces LARI, a new dataset designed to benchmark and enhance QA in Portuguese. Our methodology combines the capabilities of the Sabi{\'a}-7B model, fine-tuned via QLoRA on a domain-specific corpus, with human validation. We utilized the book Natural Language Processing {--} Concepts, Techniques, and Applications in Portuguese (2nd Edition), as a case study for content extraction. The generated instances underwent expert human evaluation, achieving an average quality score of 4.47 out of 5. The final dataset, comprising 464 context-question-answer triples, is made publicly available to the community, offering a valuable resource for future research in low-resource settings."
}