What is Calibration?

Aligning user confidence in AI outputs with the system's actual reliability in each task.

How well a model performs on new, unseen data outside the training set.

How accurately a model's claims match verifiable real-world information.

A common objective function used to train classification models by penalizing incorrect probabilities.

A statistical range that likely contains the true value of a measured model metric.

A model that scores a query and document together in one pass for high-accuracy relevance judgments.