Unverified90% confidenceFactTime unknown
Scaling Law描述了Transformer模型性能与参数量、数据量、计算量之间存在可预测的幂律关系
1
Sources
90%
Confidence
Long-term
Relevance
6/3/2026
First Seen
Sources
Demystifying Transformer: A Word-Continuation Function, Deconstructed
bilibiliAI算法工程师Fiona
Related Entities
Related Claims
VerifiedThe 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.73% similarUnverifiedIn the Transformer architecture, there is an approximately linear relationship between model parameter count and inference latency.70% similarVerifiedThe 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.69% similarUnverifiedScaling Law research has found that model performance exhibits a smooth power-law relationship with the number of model parameters N, dataset size D, and training compute C69% similarVerifiedScaling Law refers to the predictable and regular improvement in model capability as the number of parameters and the volume of training data increase.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/40179API
curl https://kongchang.com/api/v1/knowledge/claims/40179MCP
get_claim(id=40179)