Concept
LLM judge
An LLM judge is a large language model used to score or compare other models' outputs, standing in for a human rater or a brittle string-matching metric. Think of it like a unit test's assertion, except the assertion is a natural-language rubric evaluated by a model rather…
The rest of “LLM judge” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→