AI Glossary Term

What is Cross-Encoder?

Definition

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

Related terms

Pass@k
A code-evaluation metric measuring the chance that at least one of k generated samples passes the tests.
Calibration
How well a model's confidence scores match actual correctness probabilities.
Classification
A task where a model assigns an input to one or more predefined categories.
Cross-Entropy Loss
A common objective function used to train classification models by penalizing incorrect probabilities.
API (Application Programming Interface)
A structured way for one software system to send requests to and receive responses from another system.
Domain Adaptation
Methods that transfer a model trained in one domain to perform better in another domain.

Learn more in our free guides

AutoencodersCross-ValidationSparse Autoencoders for InterpretabilityCross-Encoders vs Bi-Encoders
Browse the full AI GlossaryExplore all free AI guides