Episode 16: Med-PaLM or Facepalm? A Second Opinion On LLMs In Healthcare (feat. Roxana Daneshjou), August 28, 2023
Mystery AI Hype Theater 3000
00:00
Evaluating Large Language Models in Medicine
The chapter focuses on the evaluation of large language models in the medical field. It discusses the shortcomings in using metrics like medical license exam scores and critiques the evaluation methods used for Med-PaLM. The chapter also explores the challenges of rating work in healthcare and highlights the limitations and biases present in quality ratings.
Transcript
Play full episode
