AI Glossary Term

What does “Groundedness” mean?

Definition

The degree to which an AI response is supported by source data or retrieved evidence.

Browse the full AI Glossary Explore all free AI guides

How Groundedness works

Example

A support bot cites a refund policy paragraph for each claim. A checker confirms the claim appears in the cited text. A sentence saying refunds are instant has no support and is flagged.

Why it matters

Grounded answers are easier to verify and less likely to be invented. Groundedness is checked against provided sources, not against the whole world.

Common questions

Groundedness vs factuality?

Groundedness asks whether the answer is supported by the given sources. Factuality asks whether it is true in the world.

How is it measured?

By human review or automated checks that compare each claim with the source text.

Does it guarantee correctness?

No. If the sources are wrong, a grounded answer can be wrong.

ExplainabilityThe degree to which a model's behavior can be interpreted and explained to humans.Safety CaseA structured argument, supported by evidence, that an AI system is safe for a defined context of use.Zero Data RetentionA policy where request/response payloads are not stored after processing beyond short-lived operational windows.CitationsReferences to source passages or documents included in a model's response to support its claims.GeneralizationHow well a model performs on new, unseen data outside the training set.Algorithmic BiasSystematic unfairness in model outputs caused by skewed data, assumptions, or modeling choices.