Re:Calculating Percentage-Based Confidence from Similarities...
by serengil on Thursday September 04, 2025 @12:48PM
(#45129278)
We use cosine or Euclidean distances for embedding models to make hard classifications. But this has a big limitation: no measure of confidence and no interpretability.
Instead, building a logistic regression model can turn distances into percentage based confidence scores. This also accounted for how a small decrease in distance affects the confidence score—similar to how a derivative measures sensitivity.
Instead, building a logistic regression model can turn distances into percentage based confidence scores. This also accounted for how a small decrease in distance affects the confidence score—similar to how a derivative measures sensitivity.