Chain of Thought Prompting Elicits Reasoning in Large Language Models

By Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed H. Chi, Fei Xia, Quoc Le, Quoc V. Le, Denny Zhou. Neural Information Processing Systems, 2022

20,310 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Networks and Communications, Computer Vision and Pattern Recognition, Large Language Models, Prompting & Reasoning

View Paper: https://arxiv.org/abs/2201.11903

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Jianfeng Gao
  3. Luke S. Zettlemoyer
  4. Percy Liang
  5. Quoc V. Le
  6. Yoshua Bengio
  7. Yejin Choi
  8. Graham Neubig

In Computer Networks and Communications

  1. Sergey Levine
  2. Chelsea Finn
  3. Philip S. Yu
  4. Jiawei Han
  5. Ion Stoica
  6. Xifeng Yan
  7. Wenhu Chen
  8. Denny Zhou

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Trevor Darrell
  4. Xiaogang Wang
  5. Jitendra Malik
  6. Ming-Hsuan Yang
  7. Andrew Zisserman
  8. Cordelia Schmid

In Large Language Models

  1. Luke S. Zettlemoyer
  2. Yejin Choi
  3. Hinrich Schütze
  4. Mohit Bansal
  5. Timo Schick
  6. Jianfeng Gao
  7. Noah A. Smith
  8. Furu Wei

In Prompting & Reasoning

  1. Luke S. Zettlemoyer
  2. Denny Zhou
  3. Hannaneh Hajishirzi
  4. Yejin Choi
  5. Jie Huang
  6. Swaroop Mishra
  7. Mohit Bansal
  8. Kevin Chen-Chuan Chang

Citations in the corpus