Verified90% confidenceFactExact time
The Chain-of-Thought prompting paper published in 2022 by Jason Wei et al. of Google Brain was the first to systematically demonstrate that adding step-by-step reasoning examples significantly improves the accuracy of large models such as PaLM on mathematical reasoning tasks
8
Sources
90%
Confidence
Long-term
Relevance
7/14/2026
First Seen
Sources
口语化采样登顶ICML：提示工程配得上顶会吗？
Related Claims
Unverified2021年的Chain-of-Thought Prompting论文证明，通过在提示词中加入推理步骤示例，模型的数学推理准确率可提升数十个百分点80% similarUnverifiedChain-of-Thought (CoT), proposed by Wei et al., improves accuracy on complex mathematical and logical reasoning tasks by guiding the model to display its reasoning process step by step.79% similarVerifiedThe Chain-of-Thought prompting technique was formally proposed by the Google Brain team in the 2022 paper "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models".79% similarUnverified当模型参数量超过某一阈值，其处理复杂推理任务的能力会出现非线性跃升，这一涌现现象被Google Brain等机构的研究系统记录76% similarUnverified斯坦福大学和Google DeepMind等机构的研究表明，经过结构化重写的提示词在代码生成、逻辑推理等任务上的准确率可提升20%-40%75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/510652API
curl https://kongchang.com/api/v1/knowledge/claims/510652MCP
get_claim(id=510652)