Verified65% confidenceFactExact time
The Softmax formula with temperature parameter T is P(xᵢ) = exp(zᵢ/T) / Σexp(zⱼ/T); when T→0 it degenerates to argmax, and when T→∞ it approaches a uniform distribution
3
Sources
65%
Confidence
Long-term
Relevance
7/20/2026
First Seen
Sources
Related Claims
UnverifiedLikelihood temperature scaling raises the likelihood function to the power of 1/T (T < 1), which is equivalent to multiplying the KL term in the ELBO by a coefficient T.75% similarUnverified温度参数（Temperature）的数学本质是对Softmax函数输出的概率分布进行缩放，趋近于0时模型进行贪心解码71% similarUnverifiedADE's softmax normalization uses a temperature parameter T=0.5, controlling the balance between exploration and exploitation.71% similarUnverified采样温度T=1时保持原始概率分布，T→0时输出趋于确定性，T>1时分布更平坦、输出更随机69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/569077API
curl https://kongchang.com/api/v1/knowledge/claims/569077MCP
get_claim(id=569077)