This paper discusses the challenges of using Large Language Models (LLMs) in medical chatbots for chronic disease self-management. Accordingly, we define an architecture specifically devised to deal with issues related to reliability, clinical trials, and privacy. Two solutions are compared to prevent data disclosure: a filtering mechanism for sensitive data with an external LLM, and a locally deployed LLM using open-source models. Experimental results underscore the challenges in effectively instructing the local LLM so as to provide performances comparable to GPT-3.5.
Montagna S., Aguzzi G., Ferretti S., Pengo M.F., Klopfenstein L.C., Ungolo M., et al. (2024). LLM-based Solutions for Healthcare Chatbots: a Comparative Analysis. 345 E 47TH ST, NEW YORK, NY 10017 USA : Institute of Electrical and Electronics Engineers Inc. [10.1109/PerComWorkshops59983.2024.10503257].
LLM-based Solutions for Healthcare Chatbots: a Comparative Analysis
Montagna S.;Aguzzi G.;Ferretti S.;Magnini M.
2024
Abstract
This paper discusses the challenges of using Large Language Models (LLMs) in medical chatbots for chronic disease self-management. Accordingly, we define an architecture specifically devised to deal with issues related to reliability, clinical trials, and privacy. Two solutions are compared to prevent data disclosure: a filtering mechanism for sensitive data with an external LLM, and a locally deployed LLM using open-source models. Experimental results underscore the challenges in effectively instructing the local LLM so as to provide performances comparable to GPT-3.5.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
