Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Open Rubric System: Scaling Reinforcement Learning with Pairwise Adaptive Rubric

About

Scalar reward models compress multi-dimensional human preferences into a single opaque score, creating an information bottleneck that often leads to brittleness and reward hacking in open-ended alignment. We argue that robust alignment for non-verifiable tasks is fundamentally a principle generalization problem: reward should not be a learned function internalized into a judge, but an explicit reasoning process executed under inspectable principles. To operationalize this view, we present the Open Rubric System (OpenRS), a plug-and-play, rubrics-based LLM-as-a-Judge framework built around Pairwise Adaptive Meta-Rubrics (PAMR) and lightweight Pointwise Verifiable Rubrics (PVRs), which provide both hard-constraint guardrails and verifiable reward components when ground-truth or programmatic checks are available. OpenRS uses an explicit meta-rubric -- a constitution-like specification that governs how rubrics are instantiated, weighted, and enforced -- and instantiates adaptive rubrics on the fly by conditioning on the semantic differences between two candidate responses. It then performs criterion-wise pairwise comparisons and aggregates criterion-level preferences externally, avoiding pointwise weighted scalarization while improving discriminability in open-ended settings. To keep principles consistent yet editable across various domains, we introduce a two-level meta-rubric refinement pipeline (automated evolutionary refinement for general principles and a reproducible human-in-the-loop procedure for domain principles), complemented with pointwise verifiable rubrics that act as both guardrails against degenerate behaviors and a source of verifiable reward for objective sub-tasks. Finally, we instantiate OpenRS as reward supervision in pairwise RL training.

Ruipeng Jia, Yunyi Yang, Yuxin Wu, Yongbo Gai, Siyuan Tao, Mengyu Zhou, Jianhe Lin, Xiaoxi Jiang, Guanjun Jiang• 2026

Related benchmarks

TaskDatasetResultRank
Reward ModelingRM-Bench
Average Score89.4
53
Reward ModelingJudgeBench
Accuracy93.3
45
Reward ModelingPPE Preference ZH
Accuracy82.3
19
Reward ModelingLMArena-like Benchmarks PPE Pref ZH, In-House QA, In-House Writing v1.0
PPE Pref ZH Score82.3
18
Reward ModelingRewardBench v2
Accuracy90.7
14
Showing 5 of 5 rows

Other info

Follow for update