گائیڈ سے منسلک کوئز · مشکل سطح

Calibrating LLM Judges Against Humans Quiz

Calibrate LLM judges with shared rubrics, independent human labels, confusion matrices, suitable agreement statistics, and repeated held-out checks.

متعلقہ گائیڈ کے راستےCalibrating LLM Judges Against Humans
سوال 1 کی 8

Why is Cohen's kappa preferred over raw percent agreement when calibrating an LLM judge?