When models disagree on a prediction, it often signals risky or unclear inputs....

https://www.bookmark-zulu.win/when-models-disagree-on-predictions-it-s-a-strong-sign-that-an-input-might-be

When models disagree on a prediction, it often signals risky or unclear inputs. Measuring ensemble variance helps us spot these cases. For example, we can route the top 1-2% of high-variance cases to human review