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

Evaluates whether LLM output is relevant to the input query.

Relevance means the output directly addresses and answers the question.
Uses statement extraction: breaks output into statements, classifies each
as relevant or irrelevant, scores based on proportion of relevant content.

---

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