Unverified50% confidenceFactExact time
A white-box teacher allows access to weights and logits, supporting soft-label distillation; a black-box teacher can only provide text outputs, allowing only hard-label offline distillation.
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDistillation can be decomposed into four dimensions: hard labels/soft labels, data source, offline/online timing, and teacher identity.66% similarUnverifiedTraditional knowledge distillation typically uses soft labels output by the teacher model to transfer dark knowledge such as inter-class similarities.61% similarUnverifiedAlpaca、Vicuna采用黑盒蒸馏策略，通过收集教师模型的输出文本进行监督微调61% similarUnverified跨分词器蒸馏的标准做法是将教师top-K logits投影到学生token上，在分段边界处把教师token映射到对应学生token序列的第一个token，这是一种多对一映射59% similarUnverified标签系统相比CLIP等自由文本编码器的优势在于语义边界清晰、歧义更少，但代价是无法表达训练时未见过的概念组合59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/911345API
curl https://kongchang.com/api/v1/knowledge/claims/911345MCP
get_claim(id=911345)