Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, Denny Zhou
Summary
The paper shows that prompting a large language model with a few exemplars that include intermediate reasoning steps (a 'chain of thought') substantially improves its ability to solve multi-step reasoning problems. This reasoning ability emerges only in sufficiently large models and requires no fine-tuning. Across arithmetic, commonsense, and symbolic reasoning tasks, chain-of-thought prompting produces large gains, including a new state of the art on the GSM8K math word-problem benchmark.
Key findings
- A handful of chain-of-thought exemplars unlocks strong multi-step reasoning without any model fine-tuning.
- The benefit is an emergent property of model scale, appearing only in sufficiently large models (~100B+ parameters).
- Using a 540B-parameter model (PaLM), CoT prompting set state-of-the-art accuracy on GSM8K and improved commonsense and symbolic reasoning tasks.
Subjects & keywords
Cite this paper
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, & Denny Zhou (2022). Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. Advances in Neural Information Processing Systems 35 (NeurIPS 2022). https://arxiv.org/abs/2201.11903
@inproceedings{wei2022chainofthought,
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},
title = {Chain-of-Thought Prompting Elicits Reasoning in Large Language Models},
booktitle = {Advances in Neural Information Processing Systems 35 (NeurIPS 2022)},
year = {2022},
url = {https://arxiv.org/abs/2201.11903}
}