Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
 |
 |
 |
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.},
apice = {ChainofthoughtsNeurips2022},
author = {Jason Wei and Xuezhi Wang and Dale Schuurmans and Maarten Bosma and Brian Ichter and Fei Xia and Ed H. Chi and Quoc V. Le and Denny Zhou},
booktitle = {Advances in Neural Information Processing Systems 35: 36th Conference on Neural Information Processing Systems (NeurIPS 2022)},
doi = {10.52202/068431-1800},
editor = {Sanmi Koyejo and S. Mohamed and A. Agarwal and Danielle Belgrave and K. Cho and A. Oh},
isbn = {9781713871088},
numpages = 14,
openalex = {W7133224126},
pages = {24824--24837},
publisher = {Neural Information Processing Systems Foundation, Inc. (NeurIPS)},
title = {Chain-of-Thought Prompting Elicits Reasoning in Large Language Models},
url = {https://proceedings.neurips.cc/paper_files/paper/2022/hash/9d5609613524ecf4f15af0f7b31abca4-Abstract-Conference.html},
urlopenaccess = {https://proceedings.neurips.cc/paper_files/paper/2022/hash/9d5609613524ecf4f15af0f7b31abca4-Abstract-Conference.html},
volume = 35,
year = 2022
}
