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

https://www.bookmarkingqueen.win/model-disagreement-helps-spot-risky-inputs-by-measuring-uncertainty-like

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