Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy
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-us
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 53%Towards AI-augmented decision making in psychiatry →
- PossiblePossibly related (embedding) · 51%Benchmarking large language models against practicing clinicians on psychopathological assessment - Nature →
- LinkedLinked via arxiv author · 85%Afonso Baldo →
“Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy”
- LinkedLinked via arxiv author · 85%Hugo Pitorro →
“Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy”
- LinkedLinked via arxiv author · 85%Areti Vassilopoulos →
“Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy”
- LinkedLinked via arxiv author · 85%Anabela C. Areias →
“Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy”
- LinkedLinked via arxiv author · 85%Maya D'Eon →
“Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy”
- LinkedLinked via arxiv author · 85%Fabíola Costa →
“Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy”