@inproceedings{huang-etal-2026-zzucs,
    title = "zzucs at {P}sy{D}ef{D}etect: Bridging Long-Tail Imbalance and Clinical Rubrics for {DMRS} Defense-Level Detection",
    author = "Huang, Bin  and
      Su, Liuyuan  and
      Yuan, Kaixuan  and
      Zhao, Guanghui  and
      Zhang, Shixin  and
      Zhang, Kunli",
    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-2.3/",
    pages = "13--23",
    ISBN = "979-8-89176-435-4",
    abstract = "Detecting DMRS defense levels in emotionalsupport dialogues is challenging due to severe class imbalance and fine-grained clinical distinctions between adjacent levels, issueswell documented in psychotherapy-orientedNLP surveys (Na et al., 2025). We presentzzucs for PsyDefDetect at BioNLP 2026 (Naet al., 2026a), adopting a data{--}supervisionco-design strategy. SCCR applies stratifiedresampling to balance support across nine defense levels. CoR{--}QLoRA encodes clinical rubrics, including task contracts, taxonomy definitions, and boundary cues, into staticprompts for 8B model fine-tuning. Ablationsshow SCCR improves macro-F1 by 4.9 pointsover random oversampling. Our system fromteam zzucs, submitted on CodaBench underthe display name sly{\_}zzu with submission ID652647, achieves 0.3585 macro-F1 on the official blind-test leaderboard LB1. It ranks6th of 21 registered teams with official submissions and surpasses all published 8B baselines by 4.4 F1 points over the strongest 8Bcomparator, Ministral-8B. The code has beenreleased at https://github.com/jackssdd/zzucs{\_}psydefdetect{\_}code."
}