@inproceedings{dahl-etal-2026-tralaleros,
    title = "Tralaleros at {S}em{E}val-2026 Task 9: Multilingual Polarization Detection with Transformer-based Models",
    author = {Dahl, Adrian  and
      V{\"o}lckers, Bado  and
      Mierzwa, Adam},
    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-1.51/",
    pages = "343--353",
    ISBN = "979-8-89176-414-9",
    abstract = "We present a multilingual polarization detection system for SemEval-2026 Task 9 (Subtask 1), covering 22 languages with transformer-based models. We evaluate four strategies: data rebalancing, hyperparameter optimization, model scaling, and ensembling, and show that undersampling harms performance, while larger pretrained models improve results substantially. Our best single model, XLM-RoBERTa Large, achieves a Macro-F1 of 0.7929, with analysis showing complementary strengths across model families (e.g., RemBERT for several Indic languages and mDeBERTa for Semitic/morphologically rich languages). Ensemble gains are marginal, suggesting language-aware routing is more promising than uniform aggregation. We also provide a privacy-preserving Firefox extension that runs local ONNX inference for practical deployment without sending user text to external servers."
}