Unverified50% confidenceFactExact time
The temperature parameter T controls the smoothness of the softmax; a higher T value makes the probability distribution smoother and exposes more information about the teacher model's internal decision logic.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedModel distillation softens the teacher model's softmax outputs via temperature scaling, allowing information from low-probability classes to be transferred to the student model.72% similarUnverifiedThe core of model distillation lies in the application of the temperature softmax function, which softens the probability distribution through the temperature parameter T to reveal similarity relationships between classes70% similarUnverifiedTemperature is a hyperparameter that controls the randomness of a language model's output; it acts on logits by dividing the logit by temperature T before softmax normalization—when T<1 the distribution sharpens and output becomes more deterministic, when T>1 the distribution flattens and output becomes more random.66% similarUnverifiedLLM基于Transformer架构的自注意力机制和Softmax概率分布，通过温度参数控制采样随机性，温度趋近0时输出最高概率token，温度升高时引入更多随机性64% similarUnverifiedIn confidence-gated distillation, the distillation signal for a sample is only incorporated into training when the teacher model's prediction confidence for that sample exceeds a threshold.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1013963API
curl https://kongchang.com/api/v1/knowledge/claims/1013963MCP
get_claim(id=1013963)