stat.MLNov 18, 2026

How Reward Gain Imbalance Shapes Ranking: Rethinking Rubric-Based Reward Aggregation

Authors: Zhengyuan Fan, Zhonghua Wu, Tianyu Cheng, Qun Chen

Organizations: School of Computer Science, Northwestern Polytechnical University

Abstract

Rubric-based reinforcement learning constructs rewards for aligning large language models with human preferences, typically by equally aggregating continuous scores that a judge assigns to individual criteria. However, scoring heterogeneity across criteria can distort candidate rankings. Existing work has focused on improving judges, learning criterion weights, or refining aggregation, whereas the interaction between scoring heterogeneity and ranking remains insufficiently understood. We formalize this heterogeneity as reward gain imbalance: each criterion enters the aggregated reward with its own reward gain, the gap between its expected scores on satisfied and unsatisfied responses. Counterintuitively, our experiments show that removing this imbalance, even with ground-truth labels, lowers ranking accuracy. To explain this, we derive an exact decomposition of the reward difference between any two candidates into a base satisfaction signal, a reward gain imbalance term, and a residual term, showing that reward gain imbalance can attenuate or amplify the base signal, and finding that misrankings usually concentrate on pairs where it attenuates. Guided by this analysis, we propose the adaptive Dual-Center Clipping aggregation (DCC), which bounds each criterion's contribution to the reward difference instead of simply removing the imbalance. Using only the scores of the current candidate group, it determines a clipping interval that imposes a common upper bound on per-criterion score differences between candidates, limiting the excessive influence of extreme scores while preserving continuous judgment information....

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 15, 2026

Judging the Judges: Confidence and Disagreement in Rubrics as Rewards

Rubrics as Rewards (RaR) extends reinforcement learning to non-verifiable domains by using an LLM judge to score responses against a structured rubric. Prior work has focused on improving the rubric or strengthening the single judge, with comparatively little attention to how different single or multiple judges might be used during RaR training. We first show that judge identity alone produces a substantial spread in scores when training Qwen3-4B-Base on RaR-Medicine and RaR-Science across five frontier and open-weight judges. Building on this, we propose RaRE (Rubrics as Rewards with Ensembles), a novel judge ensemble strategy for RaR with two mechanisms: a soft-Likert reward that uses judge logprobs to weight more confident judges more heavily, and a drop-on-disagreement mask that excludes high-disagreement rollouts from the GRPO update. We find that this design is critical: while a naive average of judge scores fails to outperform the best single judge, RaRE outperforms every single-judge RaR variant on both HealthBench and GPQA Diamond, with per-theme analysis showing that it inherits the complementary strengths of its constituent judges. Our findings establish judge ensembling as a compelling axis for improving RaR.
May 19, 2026

Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR

Reinforcement learning with verifiable rewards has made post-training highly effective when correctness can be checked automatically. However, many important model behaviors require satisfying several qualitative criteria at once. Rubric-based rewards address this setting by grading prompt-specific criteria and aggregating them into a scalar reward. Yet standard static aggregations conflate a criterion's human-assigned importance with its current usefulness as an optimization signal. We show that this assumption breaks down in rubric RL: many important criteria are already saturated or currently unreachable, while criteria that distinguish rollouts are not necessarily those with the largest human weights. We introduce POW3R, a policy-aware rubric reward framework that preserves human weights and category balance as the rubric objective while adapting criterion-level reward weights during training. POW3R uses rollout-level contrast to emphasize criteria that currently separate the policy's outputs, making the GRPO reward more informative without changing the underlying evaluation target. Across three base policies on two datasets spanning multimodal and text-only settings, POW3R wins 2424 of 3030 base-policy/metric comparisons, improving both mean rubric reward and strict completion (the fraction of prompts whose response satisfies every required rubric criterion) over vanilla GRPO with rubric rewards, and reaches the same plateau in 2.52.5--4×4\times fewer training steps. Rubric rewards should therefore distinguish what should matter in the final answer from what can teach the current policy.
Oct 19, 2026

Intra-Rubric Reward Divergence: Mitigating Rubric Hacking through Latent Dimension Recovery and Balancing

Rubric hacking limits both performance and training robustness in rubric-based reinforcement learning. By decomposing rubrics into sub-dimensions, we reveal the Intra-Rubric Reward Divergence: as the total rubric score increases, certain sub-dimension scores systematically decrease, suggesting the model sacrifices specific quality aspects to optimize the aggregated objective. From the sub-dimension perspective, we observe two phenomena: (1) dimension imbalance, causing the policy to favor heavily covered dimensions; (2) dimension absence, leading to a systematic gap between rewards and true quality. To mitigate these issues, we propose Fair-Race Dimension Aggregation (FRDA), which has generations compete within each dimension separately to mitigate rubric imbalance, and Residual Semantic Dimension Completion (RSDC), which mines evaluation dimensions implicitly encoded in a holistic preference signal to complete rubric coverage. Experiments in chat, science, and medical domains indicate that FRDA mitigates rubric hacking with more stable improvements, while RSDC outperforms both single-reward training and naive multi-reward aggregation, yielding generally higher-quality responses.