An Active Inference Strategy for Prompting Reliable Responses from Large Language Models in Medical Practice
This addresses the critical need for safe and effective LLM use in medical practice, though it appears incremental as it builds on existing prompting and validation methods.
The researchers tackled the problem of unreliable LLM responses in medical contexts by developing a framework that restricts knowledge to validated medical datasets and uses an actor-critic prompting protocol based on active inference. In a validation study with 100 patient queries, LLM-generated responses for cognitive behavior therapy for insomnia received high ratings from expert therapists, often exceeding those of therapist-generated appropriate responses.
Continuing advances in Large Language Models (LLMs) in artificial intelligence offer important capacities in intuitively accessing and using medical knowledge in many contexts, including education and training as well as assessment and treatment. Most of the initial literature on LLMs in medicine has emphasized that LLMs are unsuitable for medical use because they are non-deterministic, may provide incorrect or harmful responses, and cannot be regulated to assure quality control. If these issues could be corrected, optimizing LLM technology could benefit patients and physicians by providing affordable, point-of-care medical knowledge. Our proposed framework refines LLM responses by restricting their primary knowledge base to domain-specific datasets containing validated medical information. Additionally, we introduce an actor-critic LLM prompting protocol based on active inference principles of human cognition, where a Therapist agent initially responds to patient queries, and a Supervisor agent evaluates and adjusts responses to ensure accuracy and reliability. We conducted a validation study where expert cognitive behaviour therapy for insomnia (CBT-I) therapists evaluated responses from the LLM in a blind format. Experienced human CBT-I therapists assessed responses to 100 patient queries, comparing LLM-generated responses with appropriate and inappropriate responses crafted by experienced CBT-I therapists. Results showed that LLM responses received high ratings from the CBT-I therapists, often exceeding those of therapist-generated appropriate responses. This structured approach aims to integrate advanced LLM technology into medical applications, meeting regulatory requirements for establishing the safe and effective use of special purpose validated LLMs in medicine.