Rehber bağlantılı sınav · Sert Seviye

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.

İlgili kılavuz yollarıCalibrating LLM Judges Against Humans
Soru 1 arasında 8

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