An LLM-based system simulates embodied virtual patients for ACT psychotherapy training and supplies automated fidelity feedback, with expert validation of realism and quantitative comparison showing GPT-4o-mini achieves MAE of 6.12 against human ratings.
Psychotherapy for Chronic In- and Outpatients with Common Mental Disorders: The “Choose Change
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.HC 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
The paper describes Mind Companion, an LLM-based embodied conversational agent for process-based psychotherapy, with evaluations indicating that GPT-5.2 outperformed human therapist responses in expert ratings on understanding, collaboration, and alignment.
citing papers explorer
-
Toward Accessible Psychotherapy Training Using AI-Driven Interactive Patient Avatars
An LLM-based system simulates embodied virtual patients for ACT psychotherapy training and supplies automated fidelity feedback, with expert validation of realism and quantitative comparison showing GPT-4o-mini achieves MAE of 6.12 against human ratings.
-
Mind Companion: An Embodied Conversational Agent for Process-Based Psychotherapy
The paper describes Mind Companion, an LLM-based embodied conversational agent for process-based psychotherapy, with evaluations indicating that GPT-5.2 outperformed human therapist responses in expert ratings on understanding, collaboration, and alignment.