LLM As Judge

Design and validate LLM-as-judge scoring — pairwise vs pointwise, bias correction, anchor calibration, and the cases where a judge is the wrong tool. Use when the user is building an eval, scoring open-ended outputs, or comparing model versions and mentions LLM-as-judge, model grader, pairwise comparison, position bias, length bias, judge calibration, meta-eval, or asks "how do I score open-ended responses?" / "is my LLM-judge biased?".

cobusgreyling Updated 11.8k repo stars
Skills cross-link graph

File contents

cobusgreyling/agent-skills commit 22d36b7b72

Frequently asked questions

npx get-skill add cobusgreyling/llm-as-judge