This study investigates the use of Large Language Models (LLMs) in interactive language therapy for high-functioning autistic adolescents. The research evaluates the LLM’s ability to engage in empathetic and adaptable interactions within a therapeutic setting. The evaluation was conducted by a panel of psychologists and psychiatrists using a specially developed scorecard. The results indicate that LLMs hold significant promise as supportive tools in therapy, demonstrating strengths in empathetic engagement and adaptability in conversation. However, challenges in achieving the depth of personalization and emotional understanding characteristic of human therapists were noted. The study also highlights the importance of ethical considerations in the application of AI in therapeutic contexts.
Publication date: 12 Nov 2023
Project Page: https://arxiv.org/abs/2311.09243v1
Paper: https://arxiv.org/pdf/2311.09243
