用大模型自动评估心理治疗保真度
原标题：Scaling Therapy Supervision: Assessing Psychotherapy Fidelity Using Large Language Models
AI 摘要
该研究提出用大语言模型自动化心理治疗保真度评估，以缓解人工专家审查的瓶颈。作者在420份真实长程CBT转录上评估三个开放权重模型，发现细粒度类别分解结合证据优先推理准确率最高，9B的Qwen3.5-9B系统偏差最小。研究还在独立RCT数据上验证了框架能区分CBT与非CBT会话，并通过专家用户研究确认其能生成可操作的临床督导反馈。
正文节选
Scaling Therapy Supervision: Assessing Psychotherapy Fidelity Using Large Language Models Abstract Psychotherapy fidelity assessment measures how faithfully a therapist adheres to a treatment protocol, a critical determinant of positive patient outcomes. However, fidelity assessment is bottlenecked by manual expert review, rendering the process labor-intensive and unscalable. To scale therapy supervision and support clinician self-learning, we present an integrated application of large language