Roleplaying with Structure: Synthetic Therapist-Client Conversation Generation from Questionnaires

2025-10-29

AI Summary

Privacy regulations and scarcity of authentic therapeutic dialogue data hinder clinical validity in mental health AI research. To address this, we propose SQPsych: a framework that constructs client profiles from structured psychological questionnaires and integrates cognitive behavioral therapy (CBT) principles to guide open-weight large language models (LLMs) in generating role-play-based synthetic dialogues; it supports local deployment to mitigate data security risks associated with closed-source models. The resulting SQPsychConv corpus undergoes joint evaluation by clinical experts and LLMs, demonstrating high clinical authenticity. Fine-tuning an LLM on SQPsychConv yields SQPsychLLM, which significantly outperforms baseline models in counseling competency and achieves consistent performance gains across diverse mental health support tasks. This work establishes the first synthetic dialogue paradigm that simultaneously ensures privacy compliance, clinical alignment, and scalability.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Safety and Robustness
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Large language models for search
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

The development of AI for mental health is hindered by a lack of authentic therapy dialogues, due to strict privacy regulations and the fact that clinical sessions were historically rarely recorded. We present an LLM-driven pipeline that generates synthetic counseling dialogues based on structured client profiles and psychological questionnaires. Grounded on the principles of Cognitive Behavioral Therapy (CBT), our method creates synthetic therapeutic conversations for clinical disorders such as anxiety and depression. Our framework, SQPsych (Structured Questionnaire-based Psychotherapy), converts structured psychological input into natural language dialogues through therapist-client simulations. Due to data governance policies and privacy restrictions prohibiting the transmission of clinical questionnaire data to third-party services, previous methodologies relying on proprietary models are infeasible in our setting. We address this limitation by generating a high-quality corpus using open-weight LLMs, validated through human expert evaluation and LLM-based assessments. Our SQPsychLLM models fine-tuned on SQPsychConv achieve strong performance on counseling benchmarks, surpassing baselines in key therapeutic skills. Our findings highlight the potential of synthetic data to enable scalable, data-secure, and clinically informed AI for mental health support. We will release our code, models, and corpus at https://ai-mh.github.io/SQPsych

Problem

• Generating synthetic therapy dialogues using structured questionnaires and client profiles
• Overcoming data privacy restrictions with open-weight LLMs for mental health AI
• Creating clinically-grounded CBT conversations for anxiety and depression treatment

Innovation

• Generates synthetic therapy dialogues using structured profiles
• Employs open-weight LLMs for privacy-compliant data generation
• Fine-tunes models on CBT-grounded therapist-client simulations