Psychotherapy is a primary treatment for many mental health conditions, yet the interplay among therapist behaviors, client responses, and the therapeutic relationship is difficult to study at scale, as process research has relied on labor-intensive human coding. We develop and validate a computational framework for modeling therapist-client interaction, using large language models (LLMs) to measure therapist behaviors (empathy, exploration), relational quality (rapport), and client outcomes (self-disclosure, self-directed and outward-directed negative emotion). After validating model-generated scores against human annotations (ICC = 0.45-0.81; rapport 0.81, self-disclosure 0.78), we apply these measures to roughly 2,000 hours of transcripts from the Alexander Street corpus and use Structural Equation Modeling to estimate moment-to-moment relationships among therapist behaviors, rapport, and subsequent client responses, controlling for prior client state and context. Therapist empathy and exploration directly predict increased client disclosure and shifts in emotional expression; empathy is more strongly associated with self-directed than outward-directed negative emotion, suggesting greater acknowledgment of internal distress, while exploration increases disclosure and emotional elaboration. Rapport does not directly amplify disclosure or emotional intensity but instead moderates the associations between therapist behaviors and client affect, potentially contributing to reductions in internal distress. These results show that LLM-based measurement combined with structural modeling can capture core therapeutic processes at scale, with empathy and exploration acting directly and rapport as a contextual moderator, providing a foundation for precision modeling of psychotherapy and for scalable therapist training and AI-supported clinical education.

翻译：心理治疗是多种心理健康问题的主要治疗方式，然而治疗师行为、来访者反应与治疗关系间的相互作用难以大规模研究，因为过程研究依赖劳动密集型的人工编码。我们开发并验证了一个基于大语言模型（LLM）的计算框架，用于建模治疗师-来访者互动：利用LLM测量治疗师行为（共情、探索）、关系质量（融洽关系）及来访者结果（自我表露、自我导向与外部导向的负性情绪）。在通过人类编码验证模型评分后（组内相关系数ICC=0.45-0.81；融洽关系0.81，自我表露0.78），我们将这些指标应用于亚历山大街语料库约2000小时的治疗记录，并采用结构方程模型估计治疗师行为、融洽关系与后续来访者反应之间的实时关系，同时控制来访者先前状态与情境。治疗师共情与探索直接预测来访者表露增加及情绪表达转变；共情与自我导向负性情绪的关联强于外部导向负性情绪，提示其对内在痛苦的更多认可，而探索则增强表露与情绪精细化。融洽关系并不直接放大表露或情绪强度，而是调节治疗师行为与来访者情感之间的关联，可能有助于减少内在痛苦。这些结果表明，基于LLM的测量结合结构建模可大规模捕捉核心治疗过程——共情与探索发挥直接作用，融洽关系则作为情境调节因子——为心理治疗的精准建模、可扩展的治疗师培训及基于AI的临床教育奠定基础。