An active inference strategy for prompting reliable responses from large language models in medical practice.

ABSTRACT: Continuing advances in Large Language Models (LLMs) are transforming medical knowledge access across education, training, and treatment. Early literature cautions their non-determinism, potential for harmful responses, and lack of quality control. To address these issues, we propose a domain-specific, validated dataset for LLM training and an actor-critic prompting protocol grounded in active inference. A Therapist agent generates initial responses to patient queries, while a Supervisor agent refines them. In a blind validation study, experienced cognitive behavior therapy for insomnia (CBT-I) therapists evaluated 100 patient queries. For each query, they were given either the LLM's response or one of two therapist-crafted responses-one appropriate and one deliberately inappropriate-and as

SUBMITTER: Shusterman R 

PROVIDER: S-EPMC11847020 | biostudies-literature | 2025 Feb

REPOSITORIES: biostudies-literature