গাইড লিঙ্ক ক্যুইজ · কঠিন স্তর

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.

সম্পর্কিত গাইড পাথCalibrating LLM Judges Against Humans

প্রশ্ন 1 এর 8

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