Why a high kappa score still does not make an LLM judge trustworthy

IanArawjo · x · 2026-07-21

A follow-up explanation of the same metric issue: agreement statistics are more sensitive to random disagreements than to a consistent offset.

If an LLM is biased by a nearly constant amount — for example, always scoring one point above or below human raters — inter-rater alignment metrics may still look fine. That means a high kappa score does not necessarily mean the judge is truly reliable.

Takeaway

Related event: Study Warns: Unchecked LLM Judges Yield High False Positives(7 posts)→

Original post →

More from Research

Research channel →