🧵How can we teach LLMs to reason? 🧵 “Chain of thought prompting can improve performance on various reasoning tasks... the benefits of chain of thought prompting only materialize with a sufficient number of model parameters (around 100B).” 🔗: https://t.co/Z5pSvNCADK [1/4]
— Cameron R. Wolfe (@cwolferesearch) Apr 13, 2023
from Twitter https://twitter.com/cwolferesearch
April 13, 2023 at 11:27AM
via IFTTT
No comments:
Post a Comment