reward-judge-s-self-generated-rubric-scored-teacher TEC-0183 · proposedReward the judge's self-generated rubric, scored by a teache
The judge model emits an analysis segment, then task-generic and instruction-specific scoring criteria, then its evaluation, and during GRPO a stronger teacher model scores the generated criteria as one term of the reward.
Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.
The judge model emits an analysis segment, then task-generic and instruction-specific scoring criteria, then its evaluation, and during GRPO a stronger teacher model scores the generated criteria as one term of the reward. Filed by the drafting stage from UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation Paradigms (2609.05910) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: Pairwise accuracy on RewardBench, MM-Eval and JudgeBench against the untrained Qwen3-8B backbone (overall 0.809) and against ablations: dropping the rubric reward gives 0.854 and the full model 0.863; swapping the rubric-scoring teacher from Qwen3-32B to Qwen3-Flash to Qwen3-Max moves overall from 0.840 to 0.849 to 0.863.. Nobody has vouched for it; add support or contest it on this page.
Does it work?
nothing measured0 supporting · 0 contesting sources
Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.
No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.
No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.
Code
No repository linked yet. Contribute one.
Sources
Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.