Hallucination

What it is

A hallucination is output from a language model that reads as confident and well-formed but is not supported by any source the model was given. The research literature distinguishes output that contradicts the provided source from output that simply cannot be verified against it; both are fluent, and neither is marked as uncertain in the text itself.

Why it matters

Hallucination is a property of generation, not of retrieval — the model produces text whether or not evidence exists for it. This matters for company claims because a model asked about your pricing or your certifications will answer either way, and the answer will read exactly as authoritative as a correct one. Grounding and retrieval boundaries reduce the rate; a maintained record of what is actually true is what makes the reduction measurable rather than assumed.