Generative AI & LLMs beginner

Hallucination

Also called: confabulation

Fluent, confident output that is simply false — the defining failure mode of language models.

A hallucination is content the model generates because it is statistically plausible, not because it is true. It is a structural consequence of next-token prediction rather than a bug to be patched: the model optimises for plausible, and plausible and true usually coincide, right up until they do not. Grounding, retrieval, and verification reduce it; nothing eliminates it.

In practice: Invented case citations, invented DOIs, invented API endpoints — all classic, all confidently formatted.

Related terms

Where this comes up