[2201.11903] 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.

[2201.11903] Chain-of-Thought Prompting Elicits Reasoning in Large Language Models Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Computation and Language arXiv:2201.11903 (cs) [Submitted on 28 Jan 2022 ( v1 ), last revised 10 Jan 2023 (this version, v6)] Title: Chain-of-Thought Prompting Elicits Reasoning in Large Language Models Authors: Jason Wei , Xuezhi Wang , Dale Schuurmans , Maarten Bosma , Brian Ichter , Fei Xia , Ed Chi , Quoc Le , Denny Zhou View a PDF of the paper titl

related reading

• [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• Language Models Perform Reasoning via Chain of Thoughtai.googleblog.com
• [2412.06769] Training Large Language Models to Reason in a Continuous Latent Spacearxiv.org
• [2205.11916] Large Language Models are Zero-Shot Reasonersarxiv.org
• Training Large Language Models to Reason in a Continuous Latent Spacearxiv.org
• [2507.11473] Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safetyarxiv.org
• the-illusion-of-thinking.pdfml-site.cdn-apple.com
• [2510.24941] Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thoughtarxiv.org
• [2504.10615] Beyond Chains of Thought: Benchmarking Latent-Space Reasoning Abilities in Large Language Modelsarxiv.org
• [2603.07267] How to Steal Reasoning Without Reasoning Tracesarxiv.org
• [2405.18915] Towards Faithful Chain-of-Thought: Large Language Models are Bridging Reasonersar5iv.labs.arxiv.org
• Language Models can Solve Computer Tasksarxiv.org