Bài kiểm tra có liên kết hướng dẫn · Cứng Cấp độ

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.

Đường dẫn hướng dẫn liên quanCalibrating LLM Judges Against Humans
Câu hỏi 1 của 8

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