# Hallucinations

A hallucination is an agent stating something its sources don't support. The term covers three
distinct properties of an answer, and each one can be checked on its own.

Faithfulness asks whether the answer accurately represents the sources it cites. An agent can
retrieve the right document and still misquote it, invert a number, or attribute a claim the
document doesn't make.

Groundedness asks whether the answer comes from the retrieved context or from the model's own
priors, with the context left unused. An ungrounded answer can be correct whenever the prior happens
to be right, which makes it hard to notice, and it fails when the prior is wrong.

Context presence asks whether the information needed to answer was retrieved at all. When it wasn't,
the failure is in the retrieval step, before generation begins.

Hallucination is a problem because a made-up answer looks the same as a right one. The person asking
usually can't verify it themselves, and if the answer feeds a decision or another agent, the made-up
fact gets acted on.

## Questions answered under this concept

- [How can an answer be faithful to its context and still be wrong?](https://tessary.ai/answers/hallucinations/can-an-answer-be-faithful-and-still-wrong)
- [What's the difference between faithfulness, groundedness, and context presence?](https://tessary.ai/answers/hallucinations/faithfulness-vs-groundedness-vs-context-presence)
- [How do I catch agent hallucinations when my error rate stays flat?](https://tessary.ai/answers/hallucinations/how-do-you-catch-hallucinations-when-error-rate-is-flat)
- [What is a hallucination in an AI agent?](https://tessary.ai/answers/hallucinations/what-is-a-hallucination-in-an-ai-agent)
- [Why do AI agents hallucinate?](https://tessary.ai/answers/hallucinations/why-do-ai-agents-hallucinate)
- [Why does a wrong answer often look just as confident as a right one?](https://tessary.ai/answers/hallucinations/why-does-a-wrong-answer-look-confident)

---

Source: https://tessary.ai/answers/hallucinations
All concepts: https://tessary.ai/answers
From Tessary, agent reliability for AI agents in production: https://tessary.ai