ModelRefs / Grounding — AI Glossary
Grounding — AI Glossary
Constraining model outputs to verifiable evidence — retrieved documents, structured data, tool results, or citations.
Overview
Grounding is the primary defense against hallucination. RAG, function calling, and JSON-schema-constrained generation are all grounding techniques. Grounded responses include source citations that can be verified by the user.
Reference details
| Topic | evaluation |
|---|---|
| Last reviewed | 2026-06-24 |
Related terms
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Grounding — AI Glossary.
Frequently asked questions
What is Grounding?
Constraining model outputs to verifiable evidence — retrieved documents, structured data, tool results, or citations.
What concepts are related to Grounding?
Closely related concepts include rag, hallucination, function calling.