Hallucination
AI
AI
A hallucination is an AI answer that sounds convincing but is factually wrong or invented, such as a non-existent source or an incorrect figure.
It isn't a malfunction but a consequence of how these models work: they predict likely text, not verified truth. Asking about something the model doesn't know rarely yields 'I don't know'.
What reduces the risk: supply sources instead of relying on memory, ask for references you can verify, and have a human review anything that goes out.
Related terms
- LLMAn LLM (Large Language Model) is an AI model that learns language patterns from large amounts of data to process and generate text. It works with tokens: pieces of text.
- PromptA prompt is the instruction you give an AI model. The clearer the role, goal, context and required format, the more usable the answer.
- E-E-A-TE-E-A-T stands for Experience, Expertise, Authoritativeness and Trustworthiness: the framework Google's raters use to judge whether content is reliable.
