@inproceedings{altamirano-etal-2026-servsocia,
    title = "{S}erv{S}oc{IA} at {S}emeval-2026 Task 9: Evaluating Prompt Strategies for Polarization Detection",
    author = "Altamirano, Jacob  and
      Leon P{\'e}rez, Mario  and
      Ruiz-Juarez, Bruno  and
      Chiruzzo, Luis  and
      Gomez-Adorno, Helena  and
      Balouchzahi, Fazlourrahman",
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.346/",
    pages = "2754--2759",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper presents our approach to Subtask 1 of SemEval-2026 Task 9 on multilingual polarization detection in social media texts in English and Spanish. We model the task as a prompt-based binary classification problem and systematically compare zero-shot, one-shot, and few-shot strategies across multiple large language models accessed via commercial APIs, without task-specific fine-tuning. Our controlled experimental setup enforces strict data separation and consistent decoding conditions to analyze the impact of in-context supervision across architectures and languages. Results indicate that well-structured prompting enables competitive performance, though implicit and culturally nuanced polarization remains challenging."
}