发表机构
University of Trento; University of Bari（特伦托大学; 巴里大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对心理治疗师培训可扩展性问题，提出MyMentorLLM多模态模拟环境用于CBT培训，生成2100个课程，分析情感等方面，发现不同语言模型督导质量有别，患者逼真度等需评估，证明CBT培训刻意练习模拟可行。
AI 中文摘要
心理治疗师需要专家的反复培训和监督，但可扩展性存在问题。本文介绍了MyMentorLLM，这是一个基于多模态语音和文本的刻意练习模拟环境，用于生成2100个完整的认知行为疗法（CBT）培训课程。每个课程连接一名基于《精神疾病诊断与统计手册》第5版修订版（DSM-5-TR）的患者（患有重度抑郁症、广泛性焦虑症或边缘性人格障碍）、一名实习治疗师和一名专家督导。作为初步实施，采用CBT是因为其结构化程序和基于能力的监督便于标准化模拟和评估。对课程进行了情感动态、治疗能力和诊断准确性分析。模拟患者表现出与疾病相符的情感特征，实习治疗师的表现与真实心理咨询中相似。不同语言模型的督导质量不同：大多数模型高估了受训者的能力，而原生语音对语音最接近人类分数。督导反馈在7个语言模型中的5个中使模拟心理治疗师的诊断更好，症状识别准确性随模型大小增加。这项工作表明CBT培训的刻意练习模拟是可行的，尽管患者逼真度、督导校准和有害反馈应一起评估。
英文摘要
Psychotherapists need repeated training and supervision; however, scalability is problematic. We present MyMentorLLM, a multimodal voice- and text-based deliberate-practice environment with 2,100 complete Cognitive Behavioural Therapy (CBT) sessions. Each session links a DSM-5-TR-grounded LLM patient (with major depressive, generalised anxiety or borderline personality disorder), an LLM therapist-in-training and an LLM expert supervisor (powered by Gemma-4, Gemini-3.1-Flash-Live and Qwen-3.6). Sessions were analysed for emotional dynamics, therapeutic competence and diagnostic accuracy against human psychotherapy data. Simulated patients expressed disorder-congruent emotional profiles, which therapists mirrored as in human counselling. LLM trainee competence was rated above human levels in most conditions, while native speech-to-speech was closest to human scores. Supervisor feedback improved diagnostic accuracy in 5 of 7 LLM conditions, whereas symptom identification accuracy increased with model size. This work shows deliberate practice can be simulated for CBT training, although patient fidelity, supervisor calibration and harmful feedback require evaluation via a complex systems perspective.
Comments29 pages, 5 figures, 1 table; 1 extended data table, 1 supplementary table
