Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy

2026-08-21

AI Summary

研究通过定义十个治疗动作来测量和指导大语言模型进行心理治疗，发现模型过度使用询问并忽视心理教育，提供工具可改善模型与人类治疗师的一致性。

Abstract

Users increasingly turn to large language models for emotional support, yet little is known about how these models actually conduct a psychotherapy interaction. We introduce an ontology of ten therapeutic moves: compact, function-based categories grounded in the MULTI-60 inventory, validated through an annotation campaign with five licensed psychologists, and scaled with a judge-based approach that matches expert agreement. Applying it to real counseling transcripts and model-led sessions, we compare the move distributions between human clinicians and a panel of frontier models. Models over-use inquiry at up to three times the human rate, neglect psychoeducation, and are strongly context-anchored: they carry forward strategies initiated by a human clinician but rarely initiate them themselves. Exposing the ontology as a set of tools roughly halves the mean deviation from the human move distribution and improves turn-level alignment with human therapist by 7-9 percentage points, without any fine-tuning.

Problem

• large language models
• psychotherapy
• therapeutic moves
• human clinicians

Innovation

• ontology of therapeutic moves
• MULTI-60 inventory
• judge-based approach
• context-anchored strategies
• turn-level alignment