@inproceedings{assis-etal-2025-irapuarani,
    title = "Irapuarani at {S}em{E}val-2025 Task 10: Evaluating Strategies Combining Small and Large Language Models for Multilingual Narrative Detection",
    author = "Assis, Gabriel  and
      De Azevedo, L{\'i}via  and
      De Moraes, Joao  and
      Ribeiro, Laura  and
      Paes, Aline",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.semeval-1.7/",
    pages = "38--48",
    ISBN = "979-8-89176-273-2",
    abstract = "This paper presents the Irapuarani team{'}s participation in SemEval-2025 Task 10, Subtask 2, which focuses on hierarchical multi-label classification of narratives from online news articles. We explored three distinct strategies: (1) a direct classification approach using a multilingual Small Language Model (SLM), disregarding the hierarchical structure; (2) a translation-based strategy where texts from multiple languages were translated into a single language using a Large Language Model (LLM), followed by classification with a monolingual SLM; and (3) a hybrid strategy leveraging an SLM to filter domains and an LLM to assign labels while accounting for the hierarchy. We conducted experiments on datasets in all available languages, namely Bulgarian, English, Hindi, Portuguese and Russian. Our results show that Strategy 2 is the most generalizable across languages, achieving test set rankings of 21st in English, 9th in Portuguese and Russian, 7th in Bulgarian, and 10th in Hindi."
}