mlsanityData to 14 Oct 2026

Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy

arXiv 2608.21325 ↗First posted 21 Aug 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 65 references that are in the map. First posted on arXiv 21 Aug 2026.

Builds on

18 of 65 references.

References · 18

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  4. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  5. 2025Kimi K2: Open Agentic Intelligencecited by 567
  6. 2025HealthBench: Evaluating Large Language Models Towards Improved Human Healthcited by 429
  7. 2023Tool Learning with Foundation Modelscited by 302
  8. 2023Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaborationcited by 116
  9. 2025SycEval: Evaluating LLM Sycophancycited by 108
  10. 2023Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agentscited by 77
  11. 2025On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Modelscited by 69
  12. 2024A Computational Framework for Behavioral Assessment of LLM Therapistscited by 62
6 more
  1. 2024Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversationcited by 55
  2. 2024Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactionscited by 43
  3. 2026Qwen-AgentWorld: Language World Models for General Agentscited by 28
  4. 2018Multi-label Multi-task Deep Learning for Behavioral Codingcited by 12
  5. 2025Between Help and Harm: An Evaluation of Mental Health Crisis Handling by LLMscited by 6
  6. 2025Exploring Safety Alignment Evaluation of LLMs in Chinese Mental Health Dialogues via LLM-as-Judgecited by 4

Built on by

Not cited yet.