Glossary

AI & Machine Learning

Definitions with the caveats that matter.

All glossary terms

AI & Machine Learning

Human-in-the-loop

A design pattern in which a person reviews, approves, or overrides an automated output before it has effect.

Read more
AI & Machine Learning

LLM-as-Judge

Using a large language model to score or compare outputs, often as a substitute for human evaluation.

Read more
AI & Machine Learning

Calibration

How closely predicted confidence matches observed accuracy.

Read more
AI & Machine Learning

Bias audit

A structured evaluation of whether a system performs differently across groups, languages, or content types.

Read more
AI & Machine Learning

Drift

A change in model behaviour or data distribution that degrades performance over time.

Read more
AI & Machine Learning

Model card

A short document describing a model’s intended use, training data, evaluation results, and limitations.

Read more
AI & Machine Learning

Data card

Documentation of a dataset’s provenance, composition, labelling process, and known gaps.

Read more
AI & Machine Learning

Hallucination

A confident but unsupported or fabricated output from a language model.

Read more
AI & Machine Learning

Red teaming

Adversarial testing designed to find failure modes, misuse paths, and harmful outputs.

Read more