🛰️ Daily AI Frontier
‹ back to 2026-08-23

Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy

arXiv cs.CL Medical/Healthcare AI Afonso Baldo, Hugo Pitorro, Areti Vassilopoulos, Anabela C. Areias, Maya D'Eon, FabĂ­ola Costa, Ricardo Rei, Nuno M. Guerreiro 2026-08-21

TL;DR - This paper introduces a psychologist-validated ontology of ten therapeutic moves to measure how LLMs conduct psychotherapy. Frontier models differ substantially from human clinicians, but tool-based guidance improves their alignment without fine-tuning.

  • Models use inquiry at up to three times the human rate while underusing psychoeducation.
  • LLMs tend to continue strategies introduced by human clinicians rather than initiate those strategies independently.
  • A judge-based annotation approach scales the ontology while matching expert agreement.
  • Exposing therapeutic moves as tools roughly halves deviation from human move distributions and improves turn-level alignment by 7–9 percentage points.

view merged work →