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.