Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsDownload PDF

Published: 31 Oct 2022, 18:00, Last Modified: 11 Jan 2023, 20:30NeurIPS 2022 AcceptReaders: Everyone
Keywords: Language models, natural language processing, reasoning
TL;DR: Chain of thought prompting enables models to generate intermediate reasoning steps to help solve multi-step arithmetic, commonsense, and symbolic reasoning tasks.
Abstract: We explore how generating a chain of thought---a series of intermediate reasoning steps---significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reasoning abilities emerge naturally in sufficiently large language models via a simple method called chain of thought prompting, where a few chain of thought demonstrations are provided as exemplars in prompting. Experiments on three large language models show that chain of thought prompting improves performance on a range of arithmetic, commonsense, and symbolic reasoning tasks. The empirical gains can be striking. For instance, prompting a 540B-parameter language model with just eight chain of thought exemplars achieves state of the art accuracy on the GSM8K benchmark of math word problems, surpassing even finetuned GPT-3 with a verifier.
Supplementary Material: pdf
13 Replies