@inproceedings{chen-pang-2026-pingan,
    title = "{P}ing{A}n-{NLP} at {S}em{E}val-2026 Task 9: Multi-Stage Alignment via {GRPO} and Tiered Ensemble Voting for Multilingual Polarization Detection",
    author = "Chen, Diyang  and
      Pang, Youzhen",
    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-1.354/",
    pages = "2810--2816",
    ISBN = "979-8-89176-414-9",
    abstract = "This submission describes the PingAn-NLP system for SemEval-2026 Task 9 Subtask 3, identifying polarization manifestations in 18 languages. We employ a tiered optimization framework integrating Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO). Key technical innovations include synthetic reasoning distillation from a 235B teacher model , a Smart-Tradeoff reward function designed to mitigate extreme label imbalance , and a tiered ensemble voting strategy that adaptively adjusts decision thresholds based on language resources. Our 8B-GRPO-Vote system demonstrated robust internal performance in tracks like English and Hindi and officially secured second place in the Bengali, English, Odia, and Turkish competitions."
}