@inproceedings{fahim-etal-2026-perceptionlab,
    title = "{P}erception{L}ab at {P}sy{D}ef{D}etect: Overcoming Extreme Response Bias in {LLM}s via Rubric-Grounded Retrieval and Supervised Clinical Reasoning Distillation for Fine-Grained Ordinal Classification",
    author = "Fahim, Tamjid  and
      Johan, Syed  and
      Bin Maksud, Saad",
    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-2.17/",
    pages = "109--122",
    ISBN = "979-8-89176-435-4",
    abstract = "Automating the classification of psychological defense mechanisms is a critical yet challenging frontier in clinical natural language processing. General-purpose Large Language Models (LLMs) struggle to apply fine-grained ordinal frameworks like the Defense Mechanism Rating Scales due to the implicit nature of clinical cues and a fundamental clinical reasoning gap. These models exhibit severe extreme response bias, systematically gravitating toward the scale{'}s endpoints while failing to resolve nuanced, mid-level defenses. In this paper, we present our third-place system for the PsyDefDetect Shared Task at BioNLP 2026, designed specifically to overcome this failure mode. We propose a hybrid architecture that synergizes label-flattened generative retrieval with an LLM classifier fine-tuned via the distillation of supervised clinical reasoning traces. This dual approach, grounding decisions in rubric criteria while leveraging task-specific supervision, successfully mitigates the observed bias, achieving an accuracy of 67.37{\%} and a macro-F1 of 39.56{\%}. Our work provides empirical evidence that tightly integrating targeted clinical supervision with dynamic rubric-grounded retrieval significantly outperforms the raw parameter scale of un-tuned foundation models."
}