@inproceedings{diaz-etal-2025-late,
    title = "{LATE}-{GIL}-nlp at {S}emeval-2025 Task 10: Exploring {LLM}s and transformers for Characterization and extraction of narratives from online news",
    author = "Diaz, Ivan  and
      V{\'a}zquez, Fredin  and
      Luna, Christian  and
      Conde, Aldair  and
      Sierra, Gerardo  and
      G{\'o}mez - Adorno, Helena  and
      Bel - Enguix, Gemma",
    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-1.92/",
    pages = "657--665",
    ISBN = "979-8-89176-273-2",
    abstract = "This paper tackles SemEval{\textasciitilde}2025 Task{\textasciitilde}10, ``Multilingual Characterization and Extraction of Narratives from Online News,'' focusing on the Ukraine-Russia War and Climate Change domains. Our approach covers three subtasks: (1) {\{}textbf{\{}Entity Framing{\}}{\}}, assigning protagonist-antagonist-innocent roles with a prompt-based Llama{\textasciitilde}3.1{\textasciitilde}(8B) method; (2) {\{}textbf{\{}Narrative Classification{\}}{\}}, a multi-label classification using XLM-RoBERTa-base; and (3) {\{}textbf{\{}Narrative Extraction{\}}{\}}, generating concise, text-grounded explanations via FLAN-T5. Results show a unified multilingual transformer pipeline, combined with targeted preprocessing and fine-tuning, achieves substantial gains over baselines while effectively capturing complex narrative structures despite data imbalance and varied label distributions."
}