Unverified50% confidenceFactExact time
2020年Kaplan等人提出原始Scaling Law，倾向于在固定算力下优先扩大模型参数量
1
Sources
50%
Confidence
Long-term
Relevance
7/16/2026
First Seen
Sources
Related Claims
VerifiedThe scaling laws established by Kaplan et al. in 2020 indicate that model performance follows a power-law relationship with parameter count, data volume, and compute.82% similarUnverified2020年Kaplan等人提出的原始Scaling Law倾向于在固定算力下优先扩大模型参数量，导致GPT-3等模型相对训练数据量参数偏大80% similarUnverified扩展假设由OpenAI研究员Jared Kaplan等人于2020年的扩展定律论文中量化阐述，核心是模型性能与参数量、数据量、计算量存在幂律关系75% similarVerifiedThe Scaling Law was first systematically quantified by Kaplan et al. in 2020 in language model research, pointing out a power-law relationship between model performance and parameter count, data volume, and compute.74% similarUnverifiedThe Scaling Law paper by Kaplan et al. in 2020 revealed that, under a fixed compute budget, there is an optimal ratio between model parameter count and the number of training tokens (the Chinchilla optimal).74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/536161API
curl https://kongchang.com/api/v1/knowledge/claims/536161MCP
get_claim(id=536161)