اختبار مرتبط بالدليل · صعب المستوى

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.

مسارات الدليل ذات الصلةCalibrating LLM Judges Against Humans
سؤال 1 من 8

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