[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.

# link_hv3ugsn3dh.pdf ## Metadata - PDFFormatVersion=1.5 - IsLinearized=false - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - CreationDate=D:20230112010630Z - Creator=LaTeX with hyperref - ModDate=D:20230112010630Z - Custom.PTEX.Fullbanner=This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2 - Producer=pdfTeX-1.40.21 - Trapped=False ## Contents ### Page 1 Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Brian Ichter Fei Xia Ed H. C

saved by

• Eric Chang
• Jacky Zhao
• Lydia Nottingham
• Gurnoor Narula
• Arush Agrawal

related reading

• [2201.11903] Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• Training Large Language Models to Reason in a Continuous Latent Spacearxiv.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
• [2507.11473] Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safetyarxiv.org
• [2205.11916] Large Language Models are Zero-Shot Reasonersarxiv.org
• the-illusion-of-thinking.pdfml-site.cdn-apple.com
• Language Models can Solve Computer Tasksarxiv.org
• [2603.07267] How to Steal Reasoning Without Reasoning Tracesarxiv.org
• Thinking to recall: How reasoning unlocks parametric knowledge in LLMsresearch.google
• [2504.10615] Beyond Chains of Thought: Benchmarking Latent-Space Reasoning Abilities in Large Language Modelsarxiv.org
• 2402.07927arxiv.org