Conversational Self-Play for Discovering and Understanding Psychotherapy Approaches

2025/03/17 by Onno P. Kampman, Michael Xing, Kampman, Onno P +11
Computer Science · Psychology · #AI in Service Interactions #Digital Mental Health Interventions #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Mental Health via Writing #Multiagent Systems (cs.MA)

paper · pdf · doi:10.48550/arxiv.2503.16521

openalex publication_date 2025/03/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper explores conversational self-play with LLMs as a scalable approach for analyzing and exploring psychotherapy approaches, evaluating how well AI-generated therapeutic dialogues align with established modalities.

Related

• Disrupted self, therapy, and the limits of conversational AI
• From Conversation to Automation: Leveraging LLMs for Problem-Solving Therapy Analysis
• LLM-based Conversational AI Therapist for Daily Functioning Screening and Psychotherapeutic Intervention via Everyday Smart Devices
• Script-Strategy Aligned Generation: Aligning LLMs with Expert-Crafted Dialogue Scripts and Therapeutic Strategies for Psychotherapy
• Roleplaying with Structure: Synthetic Therapist-Client Conversation Generation from Questionnaires