# `Tribunal.Judges.Correctness`
[🔗](https://github.com/georgeguimaraes/tribunal/blob/v1.3.6/lib/tribunal/judges/correctness.ex#L1)

Compares LLM output against an expected answer.

Correctness means the output conveys the same meaning as the expected answer.
Combines factual accuracy with semantic similarity: the output must be
factually equivalent even if worded differently.

---

*Consult [api-reference.md](api-reference.md) for complete listing*