@inproceedings{lin-etal-2026-nycu,
    title = "{NYCU}-{NLP} at {S}em{E}val-2026 Task 9: Stacking Small Language Models for Multilingual, Multicultural and Multievent Polarization Detection",
    author = "Lin, Ding-Xiang  and
      Chu, Po-Chun  and
      Lee, Lung-Hao",
    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-1.166/",
    pages = "1258--1267",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper presents the NYCU-NLP system for SemEval-2026 Task 9 on online polarization analysis. Our approach explores the effectiveness of instruction-tuned small language models (SLMs), including Phi-4 (14B), Mistral-small-3.2 (24B), and Gemma-3 (27B), with task-specific prompting strategies and combined them via a stacking ensemble to leverage complementary modeling capacities. Evaluated across 22 languages and three subtasks, our system achieved macro-averaged F1 scores of 0.8071 for Polarization Detection (Subtask 1), 0.6108 for Polarization Type Classification (Subtask 2), and 0.5111 for Polarization Manifestation Identification (Subtask 3). Notably, our approach ranked first in 15, second in 12, and third in 10 of the 62 language-specific leaderboards, demonstrating the robustness and competitiveness of stacking-based SLM ensembles in multilingual settings."
}