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

https://deansinspiringperspective.hexaforgey.com/posts/should-i-escalate-all-disagreements-to-humans

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