Definition

Grounding

Grounding is the process of retrieving external documents at answer time and constraining the model's response to them, producing citations. When grounding does not fire, the answer comes from model weights alone and typically cites nothing.

Whether grounding fires is itself a measurable property of a surface and a query type. A prompt that grounds 100% of the time on Perplexity may ground intermittently on a chat surface.

Related terms

Query fan-out Citation share

Nostimates measures grounding across twelve AI answer surfaces. Request access →

All terms

AEO (Answer Engine Optimisation)GEO (Generative Engine Optimisation)AI Overviews AI Mode Citation share n-sampling Query fan-out Share of voice (AI)Extraction success rate Surface Answer engine Citation Brand mention Mention rate Confidence interval Statistical significance Citation volatility Non-determinism Reproducibility Identity-free collection Personalisation Locale Residential proxy Bot detection Collection cost Credit Evidence retention Audit trail Parser version Canary prompt Data freshness Cadence Prompt set Head term Long-tail query Competitive set llms.txt robots.txt AI crawler Training crawler Retrieval-augmented generation (RAG)Hallucination Answer box Featured snippet Zero-click search Entity Entity salience Knowledge graph Structured data JSON-LD schema.org FAQ schema Answer-first content Chunk Embedding Semantic search Prompt injection Market coverage Sentiment analysis Position tracking White-label data