Glossary / Artificial intelligence
Hallucination
Also called: AI hallucination
A hallucination is a false or invented answer that an AI presents with confidence, as if it were true.
An LLM does not know that it does not know. It produces the most plausible next words, and a plausible sentence can be false: a date, a quotation, a legal reference, a figure.
You reduce the risk by giving the AI the reference documents, which is the principle of RAG, and by asking it to cite its sources. You cannot remove it. Every important fact needs checking.
An example
Asked about a tax rule, an AI cites a legal article by its exact number. The article does not exist.
AR Digital’s advice
Ask the AI to cite its sources, then open every link. A link that leads nowhere is the sign of an invented answer.
AR Digital / Artificial intelligence
In the same family.
- AI agentAn AI agent is a program that receives a goal, decides which steps to take and acts inside tools to achieve it.
- Artificial intelligenceArtificial intelligence covers the techniques that enable a machine to perform tasks that normally require human intelligence.
- AutomationAutomation means handing a repetitive task that used to be done by hand over to software.
- ChatGPTChatGPT is the generative AI assistant from OpenAI. It answers questions, writes, summarises, translates and analyses documents.
- ClaudeClaude is the generative AI assistant from Anthropic. It writes, analyses long documents, writes code and chains tasks together.
- Local AIA local AI is an artificial intelligence model that runs on the company’s own machines, without sending data outside.




