LiveSPX7,620-1.28%NDX29,127-1.41%US10Y4.961%+3.23%BTC76,816-1.24%ETH2,468-2.07%GOLD4,320-1.02%NVDA210.96-8.42%MSFT505.41+1.14%GOOGL349.39+3.23%
Advertisement
AI glossary

Hallucination

Fluent output that is simply not true.

A hallucination is a confident, well-formed statement with no basis in the model's inputs or in fact. It is a property of how these models generate, not a bug that can be patched out.

Models predict plausible continuations; plausibility and truth mostly overlap, and where they do not, the output is still plausible.

Mitigations are structural: retrieval so answers are grounded in real documents, citation so claims can be checked, and human review wherever the cost of a wrong answer is real.

Related terms