Verified90% confidenceFactExact time
Knowledge distillation was proposed by Hinton et al. in 2015, originally referring to training a small model using the soft label outputs of a large model.
13
Sources
90%
Confidence
Long-term
Relevance
7/8/2026
First Seen
Sources
Fable 5对决GPT-5.6 Sol：基准测试、定价与AI权力博弈深度解析
bilibili黑纹白斑马7/3/2026
Related Claims
Verified模型蒸馏（Knowledge Distillation）最初由 Hinton 等人于2015年提出，核心思想是让小模型学习大模型的软标签而非硬标签84% similarUnverifiedKnowledge distillation was systematically proposed by Hinton et al. in 2015, with the core idea of using the output probability distribution of a large model to guide the training of a small model.84% similarVerifiedKnowledge distillation was systematized by Hinton et al. in 2015; its core idea is to transfer the dark knowledge of a large model to a small model, using soft probability distributions as supervision signals.78% similarUnverifiedKnowledge distillation guides the training of a smaller model using soft labels from a larger model, whereas pruning directly inherits knowledge from the weights of the larger model.76% similarVerifiedModel distillation technology was proposed by Geoffrey Hinton's team in 2015, originally used for model compression, by having a student model fit the soft-label outputs of a teacher model.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/243172API
curl https://kongchang.com/api/v1/knowledge/claims/243172MCP
get_claim(id=243172)