Unverified50% confidenceFactExact time
2022 年 Wei 等人在《Emergent Abilities of Large Language Models》中记录，当模型规模跨越某一参数阈值时性能会出现类似物理相变的非线性跃升
1
Sources
50%
Confidence
Long-term
Relevance
7/18/2026
First Seen
Sources
Related Claims
VerifiedThe emergent capability of large language models refers to the complex reasoning ability that suddenly manifests after the parameter scale surpasses a certain threshold.74% similarUnverified2025 年 3 月的论文《Brevity Constraints Reverse Performance Hierarchies in Language Models》指出，当强大的模型被迫给出更简洁的回答时，反而更可能给出正确答案73% similarVerifiedChain-of-Thought prompting was systematically proposed by Wei et al. in 2022 in the paper 'Chain-of-Thought Prompting Elicits Reasoning in Large Language Models'.70% similarUnverifiedThe concept of 'Emergence' in large language models describes how models at sufficient scale exhibit intelligent capabilities far beyond what their individual components would suggest69% similarUnverified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68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/547730API
curl https://kongchang.com/api/v1/knowledge/claims/547730MCP
get_claim(id=547730)