@inproceedings{takushima-etal-2026-curiosai,
    title = "{C}urios{AI} at {S}em{E}val-2026 Task 10:Hybrid approaches to conspiracy span extraction and conspiracy detection",
    author = "Takushima, Hiroki  and
      Beppu, Fumika  and
      Manoj Kumar, Aiswariya  and
      Shibata, Yuki  and
      Hori, Takayuki  and
      Yamaga, Daichi",
    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-1.71/",
    pages = "497--502",
    ISBN = "979-8-89176-414-9",
    abstract = "We present CuriosAI{'}s system for SemEval-2026 Task 10, addressing Conspiracy Marker Extraction and Conspiracy Detection. For marker extraction, we employ multi-label token classification with a bidirectional transformer (DeBERTa-v3-large) to predict overlapping spans. Alternative feature-based and LLM-based approaches do not surpass the encoder baseline. For Conspiracy Detection, we compare heterogeneous models, including transformer fine-tuning, lexical classifiers, embedding-based models, and LLM-based refinement. Development-optimal models do not always generalize best; logit-level ensembling achieves the strongest test performance (F1=0.7620). These results highlight the importance of bidirectional token modeling for span extraction and calibration-aware ensembling for robust detection."
}