Chain-of-Thought Prompting Elicits Reasoning in Large Language Models (arXiv:2201.11903)

arXiv:2201.11903. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. By Jason Wei et al. (Google). Submitted 2022-01-28. Demonstrates that prompting LLMs with intermediate reasoning steps improves performance on arithmetic, commonsense, and symbolic reasoning tasks. 2026-10-10: Fetched https://arxiv.org/abs/2201.11903. Title: 'Chain-of-Thought Prompting Elicits Reasoning in Large Language Models'. Peer-reviewed venue confirmed: NeurIPS 2022. Abstract confirms generating chains of thought elicits multi-step reasoning capabilities in LLMs.