Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

root 提交于 周日, 01/21/2024 - 12:12
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.

相关内容

发布日期 08/04/2020 - 01:35
发布日期 08/04/2020 - 01:35
发布日期 10/17/2023 - 23:16
发布日期 02/18/2025 - 20:47
发布日期 01/18/2025 - 20:37
发布日期 01/31/2024 - 13:01
发布日期 02/29/2024 - 16:35