Definition

A strong LLM gets a question, one or two responses and the grading criteria, and returns a score or a preference. GPT-4 agrees with humans on MT-Bench 80%+ of the time, as often as two humans.

BiasFix
position (favors a slot)swap and average
verbosity (longer = better)length control, explicit criteria
self-enhancement (own model family)judge from another family

Used as the CAI feedback model, as reward models, in deliberative alignment and in rubrics as rewards (decompose into criteria, grade each, aggregate). As a reward signal its biases get optimized into the policy.

Appears in