Running State-of-the-art Medical LLMs on Databricks

Healthcare-specific large language models provide superior accuracy to general-purpose LLMs. This session shares current benchmarks of John Snow Labs’ Medical Large Language Models in three areas – question answering, information extraction, and chat quality – as evaluated on a combination of widely used medical LLM benchmarks and a blind evaluation by human doctors. Then, the recommended architecture for running these models on Databricks will be shared, in a way that complies with the strict security and privacy requirements of healthcare, while still enabling a fully managed, scalable, and highly performant environment.