AI Glossary Term
What does “Hallucination” mean?
When a model generates fluent but false or unsupported information.
How Hallucination works
Example
Asked for court cases supporting an argument, a chatbot invents case names and citations that look real. In a widely reported 2023 incident, lawyers submitted a brief that cited such non-existent cases and were sanctioned.
Why it matters
Fluent writing is not evidence of accuracy. Hallucinations are why important claims, citations, and numbers from AI need independent verification.
Common questions
Why do models hallucinate?
They generate likely-sounding text from patterns rather than looking facts up, so they can produce plausible statements that are false.
How can I reduce hallucinations?
Ask the model to use provided sources, use retrieval-augmented generation, request citations you can check, and verify key facts.
Will hallucinations disappear?
They have decreased with better methods but are not eliminated, so verification remains good practice.