@inproceedings{paul-etal-2026-toni,
    title = "{TONI}-{NLP} at {P}sy{D}ef{D}etect: Defense Mechanism Detection via {LLM}-based Ensemble Methods",
    author = "Paul, Durjoy  and
      Basavaraj, Arshitha  and
      Chan, Callum  and
      Perez-Rosas, Veronica  and
      Inkpen, Diana  and
      Pereira, Francisco  and
      Lossio-Ventura, Juan Antonio",
    editor = "Gupta, Deepak  and
      Demner-Fushman, Dina",
    booktitle = "Proceedings of the {B}io{NLP} 2026 (Shared Tasks)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.bionlp-2.19/",
    pages = "132--140",
    ISBN = "979-8-89176-435-4",
    abstract = "This system paper presents the approach of Team TONI-NLP to the PsyDefDetect 2026 shared task. The objective of the task was to classify utterances from helper{--}seeker conversations into nine categories: seven labels representing progressively higher levels of defensive maturity, one label indicating the absence of a defense mechanism, and one label for cases requiring additional information. We investigated several modern NLP approaches, including prompt engineering, fine-tuning, hierarchical modeling and classification using text embeddings derived from transformer-based models as well as classical embeddings such as TF-IDF. Our results show that ensemble methods performed best among our submitted systems, achieving a macro-F1 score of 0.320 and ranking 9th in the shared task out of 21 teams."
}