# Grounding

> Grounding: Giving the model relevant, trusted text in its context so its answer can be based on that text rather than memory alone.

Canonical: https://llmdojo.dev/glossary/grounding

Giving the model relevant, trusted text in its context so its answer can be based on that text rather than memory alone.

Learn it in the lesson: [Reducing hallucination](https://llmdojo.dev/learn/model-foundations/limits/reducing-hallucination) (Model Foundations · Hallucination and the Limits of Next-Token Prediction).

## Interview questions about Grounding

- [Design a RAG-based agent system: how it retrieves, how it grounds its answers, and how it enforces access control.](https://llmdojo.dev/interview/q/design-a-rag-based-agent-system-how-it-retrieves-how-it-grounds)

## Related
- [Hallucination](https://llmdojo.dev/glossary/hallucination)
- [Glossary of every term](https://llmdojo.dev/glossary)