Unverified50% confidenceFactExact time
Self-Consistency方法由Wang等人2022年提出，在数学推理、代码生成等任务上展现出显著准确率提升
1
Sources
50%
Confidence
Long-term
Relevance
7/19/2026
First Seen
Sources
Related Claims
Unverified研究表明，即使使用相同的基础模型，引入迭代反思机制后在代码生成、数学推理等任务上的准确率可提升20%-40%74% similarUnverified2021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70% similarVerifiedThe 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 tasks70% similarUnverifiedThe Chain-of-Thought technique can significantly improve model accuracy on mathematical reasoning and code generation tasks, with the most pronounced effect on large models with parameter scales exceeding 100B.68% 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%68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/565100API
curl https://kongchang.com/api/v1/knowledge/claims/565100MCP
get_claim(id=565100)