Empirical Modeling of Therapist-Client Dynamics in Psychotherapy Using LLM-Based Assessments

TL;DR

This study employs large language models and structural equation modeling to analyze psychotherapy sessions, revealing how therapist behaviors influence client responses and emotional outcomes, thus advancing computational understanding of therapy dynamics.

Contribution

Introduces automated LLM-based assessments of therapy interactions and applies SEM to large datasets, providing scalable insights into therapeutic processes.

Findings

Therapist empathy and exploration increase client disclosure.

Rapport may reduce emotional distress rather than increase expression.

Computational tools effectively capture core therapy processes.

Abstract

Psychotherapy is a primary treatment for many mental health conditions, yet the interplay among therapist behaviors, client responses, and the therapeutic relationship remains difficult to untangle. This work advances a computational approach for modeling these moment-to-moment processes. We first developed automated methods using large language models (LLMs) to assess therapist behaviors (e.g., empathy, exploration), relational qualities (e.g., rapport), and client outcomes (e.g., disclosure, self-directed and outward-directed negative emotions). These measures showed strong alignment with human ratings (mean Pearson $r = .66$). We then analyzed nearly 2,000 hours of psychotherapy transcripts from the Alexander Street corpus using Structural Equation Modeling (SEM). SEM showed that therapist empathy and exploration directly shaped client disclosure and emotional expression, whereas rapport may contribute to reductions in internal emotional distress rather than increased willingness to express it. Together, these findings demonstrate how computational tools can capture core therapeutic processes at scale and offer new opportunities for understanding, modeling, and improving therapist training.