AI Glossary

Hallucination

When a model states something false, made up or not supported by its source, such as a citation, a quote or a number that does not exist. The text often reads as fluent and natural, and grounding a model in real sources can reduce hallucination but does not remove it.

See also

  • Grounding

    Tying a model's answer to specific sources it was given, such as documents or search results, so the answer can be checked against them.

  • Retrieval-augmented generation

    A technique in which a system first searches a collection of documents for passages relevant to a question, then gives them to the model so its answer draws on those sources rather than on memory alone.

  • Sycophancy

    A model's tendency to tell people what they want to hear, agreeing with or flattering them even when they are wrong.

  • AI slop

    Low quality content made with generative AI and put out with little human care or review, such as an article, an image or a block of code.

Source: Ji et al., Survey of Hallucination in Natural Language Generation (2022) (opens in a new tab)

Cite this term.

CC BY 4.0, attribution required.

This term

Orbyt Labs, Hallucination (AI Glossary), Oct 18, 2026. https://www.orbytlabs.ai/orbyt-collective/glossary/hallucination

The dataset (JSON)

Orbyt Labs Glossaries (Oct 19, 2026), https://www.orbytlabs.ai/glossary#dataset

Last updated .