Plain English
One AI grades another AI's work.
Example
A judge model checks if an answer is grounded in the supplied document chunks.
Why it matters
Judge models scale evaluation, but they can be biased or fooled, so they need calibration.
One AI grades another AI's work.
A judge model checks if an answer is grounded in the supplied document chunks.
Judge models scale evaluation, but they can be biased or fooled, so they need calibration.