Verified record · from the answer index

validate-evaluator

Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based eval

skill:ai-evals-course/evals-skills/validate-evaluator · published by ai-evals-course · source repository