When models disagree on a prediction, metrics like ensemble variance or entropy...

https://mighty-wiki.win/index.php/Feature_Importance_Drift_vs_Distribution_Shift:_What%27s_the_Difference%3F

When models disagree on a prediction, metrics like ensemble variance or entropy can highlight risky inputs that need attention. For example, you can track the top 1-2% of cases with the highest disagreement and route them for manual review