Kedis ku xidhan hagaha · Adag Heerka

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.

Wadooyinka haga ee la xidhiidhaCalibrating LLM Judges Against Humans
Su'aal 1 ee 8

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