# Hallucination

> A confident, fluent, entirely invented answer — a citation, a figure or an API that does not exist.

The word suggests a malfunction, which is misleading. The model is doing exactly what it always does — producing text that fits the pattern of a good answer. When it knows the material, the fitting text is also true. When it does not, the fitting text is a fabrication, and nothing in the process flags the difference, including to the model itself.

This is why confidence carries no information and why the fix is architectural rather than a matter of asking the model to be careful. Give it the source material and require it to cite what it used, constrain output to a schema where the shape can be checked, verify anything that can be verified cheaply, and put a person in front of anything expensive to get wrong.

## Related terms

- https://dfieldsolutions.com/en/glossary/llm.md
- https://dfieldsolutions.com/en/glossary/rag.md
- https://dfieldsolutions.com/en/glossary/llm-evaluation.md

---

Source: https://dfieldsolutions.com/en/glossary/hallucination
DField Solutions — Dunakeszi, Hungary — dezso@dfieldsolutions.com
Booking: see https://dfieldsolutions.com/en/contact