What is a hallucination?
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.
hallucination explained in plain English
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.
Example
Practitioners refer to hallucination when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.
People also read
- Confabulation
When an AI produces a confident, fluent answer that sounds true but is factually wrong — generating plausible language without a reliable link to reality.
- AI slop
Output from a generative AI system that favors quantity over quality.
- Chain-of-Thought Prompting
Asking an AI to show its reasoning step by step before giving a final answer, which often improves accuracy on complex tasks.
- Context Window
The maximum amount of text a language model can consider at one time, measured in tokens.
- Embedding
A numerical representation of text, images, or other data that captures semantic meaning.
- evaluation
The process of measuring a model's quality or comparing different models against each other.
- Fine-tuning
The process of further training a pre-trained AI model on specialised data to improve performance on specific tasks.
- generative AI
An emerging transformative field with no formal definition.
- GPT
A family of large language models developed by OpenAI that generate human-like text.
- guardrails
Any software or process that prevents harm to humans or systems.