Home // AIHealth 2024, The First International Conference on AI-Health // View article

Priming Large Language Models for Personalized Healthcare

Authors:
Madhurima Vardhan
Deepak Nathani
Swarnima Vardhan
Abhinav Aggarwal

Keywords: Large Language Models, Personalized healthcare, fitness coaching, prompt engineering

Abstract:
Large Language Models (LLMs) have captured attention of researchers across different scientific fields. However, sensitive data access issues, model retraining, long compute time and lack of real-time results have limited the direct application of LLMs in fields such as healthcare fitness. Healthcare fitness is ripe to take advantage of the near-human efficiency and accuracy of LLMs due to ever increasing gap between human coaches and population that requires fitness coaching. In this work, we introduce a lightweight approach, priming LLMs, to develop an automated health coach that relies upon fundamental theories of behavior science and taps into the enormous potential of LLMs. We found that sentence length and conversation length were higher in primed LLMs compared to naïve context aware LLMs. Subsequently, we conducted a qualitative reviewer evaluation and report that the primed architectures were overall more appropriate and demonstrated higher empathy.

Pages: 52 to 53

Copyright: Copyright (c) IARIA, 2024

Publication date: March 10, 2024

Published in: conference

ISBN: 978-1-68558-136-7

Location: Athens, Greece

Dates: from March 10, 2024 to March 14, 2024