{"ID":2922043,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-02T09:47:57.354342003Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.00647","arxiv_id":"2606.00647","title":"LinguIUTics at PsyDefDetect: Iterative Imbalance-Aware Fine-tuning of Qwen3-8B for Psychological Defense Mechanism Classification","abstract":"Detecting psychological defense mechanisms in conversational text remains a challenging clinical NLP problem. For the PsyDefDetect 2026 shared task (nine-class utterance classification evaluated via macro F1), our team LinguIUTics achieves a macro F1-score of 0.3917 on the official positive-class leaderboard, ranking 4th out of 21 registered teams and improving over the Ministral-8B task baseline (31.48 macro F1) by 7.7 absolute points (24.4 percent relative). BERT-family encoders and zero-shot LLMs proved ineffective on rare classes due to severe class imbalance, leading us to QLoRA fine-tuning of Qwen3-8B. We leverage three key strategies: grouped stratified cross-validation (preventing leakage), minority-class round-robin lexical augmentation, and a post-processing pipeline with logit bias tuning and ensemble blending. Together, these components close much of the validation-to-leaderboard gap and substantially improve minority-class recall, driving the critical \"Unclear\" class (Level 8) from near-zero performance to an F1 score of 0.797.","short_abstract":"Detecting psychological defense mechanisms in conversational text remains a challenging clinical NLP problem. For the PsyDefDetect 2026 shared task (nine-class utterance classification evaluated via macro F1), our team LinguIUTics achieves a macro F1-score of 0.3917 on the official positive-class leaderboard, ranking 4...","url_abs":"https://arxiv.org/abs/2606.00647","url_pdf":"https://arxiv.org/pdf/2606.00647v1","authors":"[\"Shefayat E Shams Adib\",\"Ahmed Alfey Sani\",\"Md Hasibur Rahman Alif\",\"Ajwad Abrar\"]","published":"2026-05-30T09:47:29Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"LoRA\"]","has_code":false}