Papers
arxiv:2608.21325

Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy

Published on Aug 21
Authors:
,
,
,
,
,
,

Abstract

Researchers developed a validated ontology of therapeutic moves to compare human and AI counseling interactions, finding that frontier models overuse inquiry, neglect psychoeducation, and rely on human-initiated strategies, while providing the ontology as tools improves alignment with human therapists.

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.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2608.21325
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2608.21325 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2608.21325 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2608.21325 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.