Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine
by Harsha Nori, Yin Tat Lee, Sheng Zhang, Dean Carignan, Richard Edgar, Nicolo Fusi, Nicholas King, Jonathan Larson, Yuanzhi Li, Weishung Liu, Renqian Luo, Scott Mayer McKinney, Robert Osazuwa Ness, Hoifung Poon, Tao Qin, Naoto Usuyama, Chris White, ...
This page contains highlights I saved while reading Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine by Harsha Nori, Yin Tat Lee, Sheng Zhang, Dean Carignan, Richard Edgar, Nicolo Fusi, Nicholas King, Jonathan Larson, Yuanzhi Li, Weishung Liu, Renqian Luo, Scott Mayer McKinney, Robert Osazuwa Ness, Hoifung Poon, Tao Qin, Naoto Usuyama, Chris White, .... These quotes were collected using Readwise.
Highlights
Generalist foundation models such as GPT-4 have displayed surprising capabilities in a wide variety of domains and tasks. Yet, there is a prevalent assumption that they cannot match specialist capabilities without intensive training of models with specialty knowledge.
GPT-4 can exhibit a propensity to favor certain options in multiple choice answers over others (regardless of the option content), i.e., the model can show position bias
Want more like this? See all articles or get a random quote.