[2201.11903] Chain-of-Thought Prompting Elicits Reasoning in Large Language Mode...
source link: https://arxiv.org/abs/2201.11903
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
Computer Science > Computation and Language
[Submitted on 28 Jan 2022 (v1), last revised 10 Jan 2023 (this version, v6)]
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
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.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2201.11903 [cs.CL] |
| (or arXiv:2201.11903v6 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2201.11903 |
Submission history
From: Jason Wei [view email][v1] Fri, 28 Jan 2022 02:33:07 UTC (944 KB)
[v2] Wed, 6 Apr 2022 03:51:50 UTC (933 KB)
[v3] Wed, 1 Jun 2022 00:10:30 UTC (303 KB)
[v4] Mon, 13 Jun 2022 21:44:34 UTC (283 KB)
[v5] Mon, 10 Oct 2022 20:21:17 UTC (285 KB)
[v6] Tue, 10 Jan 2023 23:07:57 UTC (306 KB)
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK