AI in Medicine: From Text Prediction to Clinical Tools: How LLMs Work – Hosted by the Geisel Academy of Educators and Scholars

Overview

Large language models are the AI systems health professionals use most directly and understand least. This session traces the line from early natural language processing through word embeddings and recurrent networks to the transformer architecture behind current systems. The aim is an accurate mental model, not technical proficiency: what these systems do when they produce text, why they hallucinate, and what tokenization, embeddings, attention, temperature, fine-tuning, and prompt engineering mean in practice. A live screen-shared demonstration shows prompt structure changing output, and hallucination occurring.

Please see the event website for further details.

Accreditation

Please see the event website for accreditation information.