Unverified50% confidenceFactExact time
Distillation usually introduces a temperature parameter T to smooth the teacher's outputs; the larger T is, the flatter the distribution and the richer the dark knowledge.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedTemperature scaling calibrates a model by dividing logit values by a learnable scalar parameter T before the softmax; T greater than 1 softens the probability distribution, T less than 1 sharpens the distribution, and the main model does not need to be retrained.72% similarUnverifiedHinton在原始论文中引入温度参数T来控制概率分布的柔软程度,T越高分布越平滑,类间相似关系暴露越充分,这些类间关系被称为暗知识(Dark Knowledge)71% similarVerifiedThe higher the temperature parameter, the flatter the probability distribution output by Softmax, and the more creative and diverse the output; the lower the temperature, the sharper the distribution and the more deterministic and conservative the output.68% similarUnverifiedTemperature changes how concentrated or spread out the token probability distribution is during sampling; lower temperatures make choices more predictable, while higher temperatures allow more variation, but it does not change the knowledge the model has learned.62% similarUnverifiedAn LLM outputs a probability distribution when generating each word, and the higher the temperature the more random the sampling; even if two assistants recall the same information sources, different temperature settings can lead to different wording or even a different order of companies mentioned.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1083202API
curl https://kongchang.com/api/v1/knowledge/claims/1083202MCP
get_claim(id=1083202)