@inproceedings{abu-horaira-etal-2026-eraserhead,
    title = "Eraserhead at {P}sy{D}ef{D}etect: Prompt Design and Class Rebalancing for Psychological Defense Mechanism Detection",
    author = "Abu Horaira, Muhammad  and
      Rahman, Mehreen  and
      Chowdhury, Nahian",
    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-2.8/",
    pages = "54--58",
    ISBN = "979-8-89176-435-4",
    abstract = "We describe the Eraserhead system submitted to the PsyDefDetect shared task at BioNLP 2026, which frames psychological defense level detection as a nine-class utterance classification problem over supportive dialogue. Our system is based on Qwen3-14B and combines clinically informed prompt design, per-label oversampling, and careful inference settings for stable prediction. A central challenge of the task is strong class imbalance, with High-Adaptive responses appearing far more often than several minority classes. This makes it easy for models to favor the majority class and achieve reasonable accuracy while performing poorly on rarer categories. To address this, we iteratively adjusted oversampling targets based on error analysis and predicted label distributions across submission rounds. Our final system achieved an official macro F1 of 0.3418 on Leaderboard 1 and 0.3947 on Leaderboard 2, ranking 7th among the 21 registered teams on both leaderboards. We further analyze the main failure modes of the system, especially the difficulty of distinguishing Minor Image Distorting defenses from High-Adaptive responses and the persistent tendency to over-predict the majority class. These findings highlight the broader difficulty of modeling psychological function from text alone."
}