PulseAugur
EN
LIVE 22:48:48

AI simulates patient avatars for accessible psychotherapy training

Researchers have developed an AI system to aid in psychotherapy training by simulating patient interactions. The system uses large language models to create virtual patients for practicing evidence-based interventions like Acceptance and Commitment Therapy (ACT). An automated evaluator provides feedback on therapist responses, and expert psychologists have confirmed the realism of the patient behavior and the utility of the feedback. Quantitative analysis indicated that GPT-4o-mini was the most effective model for replicating human supervisor ratings. AI

IMPACT This AI system offers a scalable method for practicing therapeutic interventions, potentially improving therapist training accessibility and effectiveness.

RANK_REASON The cluster describes a research paper published on arXiv detailing a novel AI application.

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

AI simulates patient avatars for accessible psychotherapy training

COVERAGE [2]

  1. arXiv cs.CL TIER_1 English(EN) · Pascal Riachi, Sofie Kamber, Stella Brogna, Andrew Gloster, Rafael Wampfler ·

    Toward Accessible Psychotherapy Training Using AI-Driven Interactive Patient Avatars

    arXiv:2606.17786v1 Announce Type: cross Abstract: Training psychotherapists in evidence-based interventions such as Acceptance and Commitment Therapy (ACT) requires repeated practice with meaningful feedback, yet opportunities for safe, standardized training are limited by ethica…

  2. arXiv cs.CL TIER_1 English(EN) · Rafael Wampfler ·

    Toward Accessible Psychotherapy Training Using AI-Driven Interactive Patient Avatars

    Training psychotherapists in evidence-based interventions such as Acceptance and Commitment Therapy (ACT) requires repeated practice with meaningful feedback, yet opportunities for safe, standardized training are limited by ethical, logistical, and resource constraints. We introd…