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-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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Controllable Affective Generation via Latent Vector Steering
Large Language Models (LLMs) often produce emotionally flattened responses after alignment, limiting their effectiveness in affect-sensitive applications. In this paper, we propose EmoVec, a lightweight framework for con…
Continuous ControlEurythmic Dancing with Plants -- Measuring Plant Response to Human Body Movement in an Anthroposophic Environment
This paper describes three experiments measuring interaction of humans with garden plants. In particular, body movement of a human conducting eurythmic dances near the plants (beetroots, tomatoes, lettuce) is correlated …
Steering Language Models with Weight Arithmetic
Providing high-quality feedback to Large Language Models (LLMs) on a diverse training distribution can be difficult and expensive, and providing feedback only on a narrow distribution can result in unintended generalizat…
Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models
Personality steering in large language models (LLMs) commonly relies on injecting trait-specific steering vectors, implicitly assuming that personality traits can be controlled independently. In this work, we examine whe…
STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations
Training Data Attribution (TDA) seeks to trace a model's predictions back to its training data. The gold standard for TDA relies on causal interventions, observing how a model changes when data is added or removed, but r…
Compressive Sensing