Unverified60% confidenceFactExact time
In traditional white-box distillation, the student model can directly access the complete probability distribution (logits) of the teacher model's output layer, whereas commercial large language model APIs typically return only the final generated text or top-k token probabilities.
2
Sources
60%
Confidence
Long-term
Relevance
9/10/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedHard distillation refers to the student model directly learning the final output labels or generated text of the teacher model, while soft distillation requires the student model to learn the complete probability distribution (logits) output by the teacher model.73% similarVerifiedKnowledge distillation transfers the full probability distribution information output by the teacher model via soft labels, producing an implicit data augmentation effect.68% similarVerifiedThe essence of large language models is learning the conditional probability distribution of what the next word is given the preceding text68% similarUnverified大语言模型通过自监督预训练学习token序列的条件概率分布，本质上是统计压缩模型，无法通过统计特征区分正确与错误的数学证明66% similarVerifiedLLMs are fundamentally probability distribution systems trained on massive amounts of text, where each output is a sampling of the next most likely token rather than retrieval and reasoning based on real-world knowledge.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/886034API
curl https://kongchang.com/api/v1/knowledge/claims/886034MCP
get_claim(id=886034)