@inproceedings{shivam-etal-2026-nit,
    title = "{NIT}-Agartala-{NLP}-Team at {S}em{E}val-2026 Task 9: A Weighted Soft-Voting Ensemble Framework of Fine-Tuned {LLM}s for Binary and Multi-Label Polarization Detection",
    author = "Shivam  and
      Kumar, Manish  and
      Jamatia, Anupam",
    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-1.398/",
    pages = "3169--3181",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper presents the NIT-Agartala-NLPTeam{'}s submission to SemEval-2026 Task 9on polarization detection in textual data. Thetask comprises two subtasks: (i) binary classification to distinguish polarized from nonpolarized content, and (ii) multi-label classification to identify the specific type(s) of polarization. We propose a weighted soft-votingensemble framework that integrates multiplefine-tuned large language models (LLMs). Theprobabilistic outputs of the individual models are combined using weighted averagingto effectively leverage their complementarystrengths and enhance overall performance.Our system achieved a test macro F1-score of78.6 (26th out of 44 teams) in Subtask 1 and46.0 (18th out of 29 teams) in Subtask 2."
}