Unverified50% confidenceBenchmarkExact time
Routing queries that semantic entropy judges as uncertain to a larger expert model for processing yields accuracy improvements of up to +50 percentage points.
1
Sources
50%
Confidence
Long-term
Relevance
9/21/2026
First Seen
Sources
Related Entities
Related Claims
Unverified当不动动作占据80%以上帧时，模型通过最小化交叉熵损失可在不学习有意义特征的情况下达到80%准确率，这称为多数类捷径71% similarUnverifiedFinite-sample estimation of entropy rate faces a systematic negative bias problem, where plug-in estimators tend to underestimate the true entropy; this can be compensated using the Miller-Madow correction by adding a (k-1)/(2N) term.70% similarUnverified投机解码在代码生成等低熵任务中接受率可达70-85%，在创意写作等高熵任务中可能降至40-60%67% similarUnverifiedWhen calculated per byte, Shannon Entropy ranges from 0 to 8, with a value close to 8 indicating that the data is nearly completely random.67% similarVerifiedThe cross-entropy loss in classification tasks is essentially the negative of the log-likelihood function, and minimizing cross-entropy is equivalent to maximizing the log-likelihood of the model on the training data.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/938055API
curl https://kongchang.com/api/v1/knowledge/claims/938055MCP
get_claim(id=938055)