Glossary

LLM-as-Judge

LLM judges are cheap and scalable, and they inherit the biases of their prompts and training data. They are useful for triage and regression testing, not for final authority on contested quality judgements.

Why it matters

Using a large language model to score or compare outputs, often as a substitute for human evaluation. Understanding the term is the first step; applying it consistently is the harder part.

Browse the glossary or read the editorial standards.

Related terms

Human-in-the-loop

A design pattern in which a person reviews, approves, or overrides an automated output before it has effect.

Read more