RESEARCH PREPRINT – Analysis of Generative AI Large Language Models (LLMs) for Hyper-Specialized Transfer Learning in Medical Chatbots

Share This Post

Note: This is a preprint of an abstract of an AI research paper. At the time of writing, the paper is still being finalized for publication. A link to the final publication will be provided here once it is published.

Title: Analysis of Generative AI Large Language Models (LLMs) for Hyper-Specialized Transfer
Learning in Medical Chatbots

Authors: Boyle, Jacob; Samal, Soham; Sabale, Aarnav


Abstract:
Generative AI Large Language Models (LLMs), such as the prevalent GPT series of transformer
based models, provide unique capabilities to enable medical chatbots and medical NLP
technologies to generate more personalized responses, gain deeper insight into textual input,
and provide more comprehensive and robust responses and care to patients. However,
commercially available models are not specialized for medical usage and have previously been
shown to produce toxic text, misinformation, and inappropriate if not harmful responses.
Developing specialized medical LLMs currently requires large datasets of training examples and
significant processing time which typically are not available to the average medical practice or
startup due to high cost and time constraints. This paper proposes an alternative method to
creating new medical LLMs by developing specialized medical chatbot skills using minimal
training examples and commercially available LLMs by instructing the LLM to contextualize a
logic-based template based on a patient’s input. Two commercially available generative LLMs
were given varied amounts of training examples on a number of specialized tasks specific to
transforming a patient’s textual input into a medically appropriate output, and the outputs were
scored for medical accuracy, toxicity, personalization, appropriateness, and grammatical
correctness. Preliminary results showed that transfer outputs from generalized LLMs
outperformed generalized LLMs on toxicity and accuracy, while matching specialized LLMs on
toxicity and accuracy while improving on personalization. Using a style transfer approach can
enable the more rapid development and commercialization of medical chatbots by reducing the
time and cost required to compile data and train models while improving accuracy and safety by
reducing variables in the model.

Jacob Boyle serves as CEO and CTO of MARCo Technologies. As CEO, his primary functions include defining the company direction, managing contractors and employees, and spearheading outreach and customer discovery. As CTO, he has handled the development of MARCo, having designed and produced the existing MARCo units; coordinate with manufacturers; develop software for the online edition; and oversee continued R&D. He also served as the Technical Lead in the National Science Foundation’s I-Corps accelerator program on behalf of the company.

Subscribe To Our Newsletter

Get updates and learn from the best

More To Explore

From mood rings to mood trackers: The evolution of wearable tech

Wearable tech has come a long way since the mood ring craze of the 1970s. Today’s sophisticated devices can track our mood, stress levels, and emotional well-being. Learn how wearable tech is helping us to better understand ourselves and develop strategies for managing our mental health. … Read More

The Hidden Benefits of Anxiety: 3 Ways to Turn Your Stress into Success

Anxiety is often perceived as a hindrance, but it can also be a hidden catalyst for success. By harnessing the power of anxiety, we can enhance our focus, boost our creativity, and develop greater resilience. Learn how to turn your stress into success with these actionable tips and insights from thought leaders in the field. … Read More

Are you looking to improve your mental health?

we have someone who can help

Cute robot therapist sitting in chair
Need some time to think? Take a $200 discount with you!

Ready for a mental health upgrade? Subscribe now, snag your $200 DISCOUNT, and a shot at WINNING A FREE MARCo – your perfect mental health companion! 🎉

Discover MARCo - Discover Your Mental Health

Get personalized mental health tips and recommendations straight to your inbox, plus get discounts and giveaways for MARCo!

Get In Touch!

GRAB ONE OF 20 SPOTS REMAINING!

Reserve your marco today!

Just a $49.99 reservation fee; refundable at any time

Due to a global microchip shortage, this reservation fee will ensure that we can get the parts to make your MARCo without you waiting an extra 6-12 months!

Young man holding a robot therapist
small_c_popup.png

Sign up for MARCo

Be first in line to get the next gen mARCo

MARCo-II Pre-Order
Name (optional)
Name (optional)
First
Last