Quiz lié à un guide · Difficile Niveau

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.

Chemins de guidage associésCalibrating LLM Judges Against Humans
Question 1 de 8

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