What is…
Hallucination
When a model states something false — a fake quote, citation, or fact — with total confidence.
Because a model generates plausible text rather than retrieving verified facts, it can produce answers that sound right but aren't: invented statistics, nonexistent court cases, broken links, APIs that don't exist.
You reduce it by grounding the model in real sources (search, uploaded documents, RAG), asking it to cite and quote, allowing it to say "I don't know," and checking anything that matters. Newer models hallucinate less — not never.
💡 Think of it like
A student who didn't do the reading but writes a fluent, confident essay anyway.
📌 Example
Asking for "5 studies proving X" without web search is a classic way to get fabricated citations.
🧠 Test yourself
Which of these describes Hallucination?
Related terms
Grounding
Tying a model's answer to real, provided sources — search results, documents, data — instead of memory.
RAG (Retrieval-Augmented Generation)
Looking up relevant documents first, then having the model answer using them — grounded, current, citable.
LLM (Large Language Model)
A model trained on huge amounts of text to predict the next word — the engine behind ChatGPT, Claude, Gemini and Grok.
🎮 Learn AI by playing
40 bite-size missions, boss battles and a certificate. Free.
Start the bootcamp →☀️ One AI term every morning
Plus the day's top stories, in your inbox by 8am.