NeurIPS · 2022
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Sha, Ed Chi, Quoc V. Le +1 more
3discussions
Abstract
Shows that prompting language models with intermediate reasoning steps (chain-of-thought) substantially improves performance on complex reasoning tasks.