# Hallucination

Source: https://customlabs.io/glossary/hallucination/
Updated: 2026-09-13

Evaluation

# Hallucination

A hallucination is a confident, fluent output that is factually wrong or unsupported.

The model completes a plausible-sounding answer rather than admitting that it does not know.

It is a structural property of how these models generate text, not a bug to patch out.

Grounding through RAG and evals, not a better prompt, are the actual mitigations.

A demo that never shows a hallucination usually means its test set was too easy.

[Insight: Your RAG demo lied to you](https://customlabs.io/insights/your-rag-demo-lied/)[Insight: Evals before you ship](https://customlabs.io/insights/evals-before-you-ship/)[Field guide: Failure modes](https://customlabs.io/failure-modes/)

[← Back to the full glossary](https://customlabs.io/glossary/)

## Related terms

[Retrieval-Augmented Generation (RAG) Retrieval-Augmented Generation (RAG) retrieves relevant passages at query time and feeds them into an LLM's context.](https://customlabs.io/glossary/retrieval-augmented-generation/)[Prompt Injection Prompt injection is untrusted input crafted to override a model's system prompt or task.](https://customlabs.io/glossary/prompt-injection/)[Eval Suite (Evals) An eval suite is a versioned set of test cases that measures whether outputs are good.](https://customlabs.io/glossary/eval-suite/)

## More in Evaluation

[LLM-as-Judge LLM-as-judge uses another LLM to score a model's outputs against a rubric, at scale.](https://customlabs.io/glossary/llm-as-judge/)[Observability Observability captures traces of every prompt, retrieval, tool call, and response for debugging.](https://customlabs.io/glossary/observability/)[Shadow Deployment A shadow deployment runs a candidate release against real production traffic, offline, before release.](https://customlabs.io/glossary/shadow-deployment/)