Class Imbalance
A problem in machine learning in which the numbers of positive and negative samples differ greatly, causing distortion in evaluation metrics such as precision; it commonly arises in scenarios such as rare disease detection and fraud identification.
Core Facts
Timeline (last 90 days)
The strength of cross-prompt inference's effect is related to task characteristics: it is strongest when class imbalance and visual confusability together cause significant rare-class suppression, and its advantage weakens or even disappears when such suppression does not exist or is not pronounced.
In real systematic review data, the number of excluded articles far exceeds the number of included articles, with the ultimately included literature often accounting for only 1%–5% of the total.
All Facts (3)
When samples are severely imbalanced, Accuracy becomes misleading—a model that predicts everyone as healthy can still achieve an accuracy of over 99%.
70%UnverifiedThe strength of cross-prompt inference's effect is related to task characteristics: it is strongest when class imbalance and visual confusability together cause significant rare-class suppression, and its advantage weakens or even disappears when such suppression does not exist or is not pronounced.
50%UnverifiedIn real systematic review data, the number of excluded articles far exceeds the number of included articles, with the ultimately included literature often accounting for only 1%–5% of the total.
50%