Grounding
Tying a model's answer to specific sources it was given, such as documents or search results, so the answer can be checked against them. A grounded answer often cites where each claim came from, though a citation alone does not prove the source supports the claim.
See also
- Retrieval-augmented generation
A technique in which a system first searches a collection of documents for passages relevant to a question, then gives them to the model so its answer draws on those sources rather than on memory alone.
- Hallucination
When a model states something false, made up or not supported by its source, such as a citation, a quote or a number that does not exist.
- Semantic search
Search that finds results by meaning rather than by exact words, often by comparing embeddings, so a search for "cheap flights" can find a page about "low airfares".
- Knowledge cutoff
The date through which a model's knowledge is most extensive and reliable, which Anthropic calls its reliable knowledge cutoff.
Cite this term.
CC BY 4.0, attribution required.
Orbyt Labs, Grounding (AI Glossary), Oct 18, 2026. https://www.orbytlabs.ai/orbyt-collective/glossary/grounding
Orbyt Labs Glossaries (Oct 19, 2026), https://www.orbytlabs.ai/glossary#dataset
Last updated .