Kvíz spojený s průvodcem · Těžko úroveň

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.

Související vodicí cestyCalibrating LLM Judges Against Humans
Otázka 1 z 8

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