Retrieval & generation · Glossary term

What is Grounding?

Connecting a generated answer or action to evidence, state, or observations that the system can identify and check.

Why does Grounding matter?

Grounding gives the system a basis beyond unconstrained generation and makes unsupported claims easier to detect.

Grounding in practice

Retrieve a policy section, require the answer to cite it, and reject claims that the cited passage does not support.

What is the common confusion about Grounding?

Adding documents to a prompt creates an opportunity for grounding. It does not guarantee the model will use them correctly.

Learn Grounding in the course

Start with

  • RAG (Retrieval-Augmented Generation)

    Your LLM knows everything up to its training cutoff. It knows nothing about your company's docs, your codebase, or last week's meeting notes.

    Phase 11: LLM Engineering

Lessons that name Grounding in a title or section

  • Video-Language Models: Temporal Tokens and Grounding

    Video is not a stack of photos. A 5-second clip has causal ordering, action verbs, and event timing that an image model cannot represent.

    Phase 12: Multimodal AI

  • Multimodal RAG and Cross-Modal Retrieval

    Vision-native document RAG is one slice. Production multimodal RAG goes wider — retrieving across text, images, audio, and video for workflows like trip planning ("find me a quiet vegan brunch with…

    Phase 12: Multimodal AI

  • Multimodal Agents and Computer-Use (Capstone)

    The 2026 frontier product is a multimodal agent that reads screenshots, clicks buttons, navigates web UIs, fills forms, and completes workflows end-to-end.

    Phase 12: Multimodal AI

Taught in Phase 11: LLM Engineering.

Also covered in Phase 12: Multimodal AI.

  • RAG (Retrieval-Augmented Generation)A system pattern that retrieves evidence relevant to a request and supplies selected content to a generative model before it answers or…
  • HallucinationGenerated content that is false, unsupported by the available evidence, or inconsistent with the task's source of truth.
  • Verification GateA control point that blocks progress until defined evidence satisfies a correctness or quality criterion.
  • RerankerA second-stage model or scoring function that reorders a small candidate set using a richer comparison between the query and each candidate.
  • ChunkingDividing source material into retrievable units before indexing. Chunk boundaries, overlap, metadata, and document structure determine…
  • Content ProvenanceVerifiable information about the origin and editing history of a piece of media or other digital content, including the actors, tools,…
  • Data ProvenanceTraceable information about where data originated, who or what transformed it, which versions were used, and how derived artifacts relate…
  • Lost in the MiddleA long-context failure pattern in which model performance changes with evidence position and can degrade when relevant information sits…
  • Maximum Marginal Relevance (MMR)A selection rule that balances relevance to the query with novelty relative to items already selected.
  • Modality AlignmentLearning or establishing correspondences between representations from different modalities so semantically or temporally related items can…
  • ReActAn agent pattern that interleaves task reasoning, a concrete action, and an observation returned by the environment before deciding the…
  • Semantic CacheA cache that reuses a previous result when a new request is judged sufficiently similar under a chosen representation and threshold.
  • Visual GroundingConnecting a language expression to spatial evidence in an image or video, such as a region, object, mask, or tracked entity.

More terms in Retrieval & generation

Open the Retrieval & generation list in the glossary

This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.