# Hallucination

> When a language model generates fluent output that is false or unsupported by its sources, presented as if it were fact.

_The Agentic Web Lexicon · /glossary/hallucination · [JSON](/api/glossary/hallucination) · [all The Agentic Web Lexicon](/glossary)_

- **term:** Hallucination
- **category:** core
- **short_def:** When a language model generates fluent output that is false or unsupported by its sources, presented as if it were fact.
- **long_def:** A hallucination is a confident but ungrounded generation: the model predicts plausible tokens rather than retrieving a verified fact, so the answer can be wholly invented — a citation, a number, an API that does not exist. It is a property of next-token prediction, not a bug, which is why grounding and retrieval are used to constrain it.
- **see_also:** grounding, rag, ai-agent
- **etymology_origin:** — (verify-against-primary-at-build)
- **related_to:** grounding, rag, agentic-rag, ai-agent
- **contrast_with:** Unlike a factual error copied from a bad source, a hallucination is generated with no source at all — the model fabricates it from statistical likelihood.
- **example:** An agent asked for a library's API might invent a method that reads plausibly but does not exist; grounding the agent in the real docs is what prevents it.
- **source:** https://en.wikipedia.org/wiki/Hallucination_(artificial_intelligence)
- **status:** active
- **why_it_matters:** Hallucination is why the agentic web values grounding, structured data and verifiable sources: an agent that can retrieve a fact does not have to invent one.
- **sameAs:** https://en.wikipedia.org/wiki/Hallucination_(artificial_intelligence)
- **bridge_entity:** grounding
- **last_verified:** 2026-07-06
- **md_twin:** /glossary/hallucination.md