@inproceedings{basu-2026-neural,
    title = "Neural Nexus at {P}sy{D}ef{D}etect: Fine-Tuning {R}o{BERT}a with Focal Loss and Role-Tagged Dialogue History for Defense Level Detection",
    author = "Basu, Subhrajyoti",
    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-2.10/",
    pages = "66--70",
    ISBN = "979-8-89176-435-4",
    abstract = "We describe our system for the PsyDefDetect shared task at BioNLP 2026, which focuses onclassifying help-seeker utterances in multi-turn supportive conversations into nine psychological defense mechanism levels defined by the Defense Mechanism Rating Scales (DMRS). Our approach fine-tunes roberta-base using a composite training objective that combines focal loss, label smoothing, and squareroot dampened class weights to address the severe label imbalance present in the PSYDEFCONV corpus, where the dominant class constitutes 52{\%} of the training data. The inputrepresentation is constructed by concatenating up to eight dialogue turns with role-specific tags, separated using RoBERTa{'}s native /s tokens, followed by the target utterance marked using a [TARGET] token. Model selection is performed using macro-F1 based early stopping on a stratified 15{\%} validation split, along with cosine learning rate decay for stable optimization. Our best submission achieves an official Leaderboard 1 (positive classes) macroF1 score of 0.2556, ranking 11th among 21 registered teams."
}