Unverified50% confidenceFactExact time
斯坦福大学与谷歌联合研究表明，多步推理、代码调试、跨语言翻译等任务在特定模型规模阈值处呈现明显能力跃升
1
Sources
50%
Confidence
Long-term
Relevance
7/20/2026
First Seen
Sources
Related Claims
Unverified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% 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71% similarVerifiedThe emergent capability of large language models refers to the complex reasoning ability that suddenly manifests after the parameter scale surpasses a certain threshold.71% 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".71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/573332API
curl https://kongchang.com/api/v1/knowledge/claims/573332MCP
get_claim(id=573332)