Also known as: Hallucination (AI) Β· Hallucination (also referred to as confabulation) Β· Hallucinations
A hallucination is an AI-generated output that appears plausible or confident but is false, unsupported, misleading, or fabricated. In generative AI, hallucinations may include incorrect facts, invented sources, false citations, or reasoning that is not grounded in reliable evidence. They are commonly mitigated through grounding, constraints, verification, evaluation, and human review.
The production of plausible-seeming but factually incorrect output by a generative AI model that purports to be making an assertion about the real world. For example, a generative AI model that claims that Barack Obama died in 1865 is hallucinating.
A hallucination in generative AI is a confident response by an AI that cannot be grounded by its training data. It may be factually incorrect. In the context of text generation, it's plausible-sounding random falsehoods within its generated text content.
A side-by-side comparison of Hallucination and Confabulation. Understand how both describe plausible but unsupported or fabricated AI output, and why hallucination is often used as the broader operational term.
A side-by-side comparison of Hallucination and Misinformation. It explains how false or fabricated AI outputs differ from false or misleading information shared regardless of intent.
A side-by-side comparison of Unsupported-claim Rate and Hallucination. Understand how a measurement of unsupported claims relates to the broader failure of false or fabricated AI output.