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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Reward Modeling | RM-Bench | Average Score89.4 | 53 | |
| Reward Modeling | JudgeBench | Accuracy93.3 | 45 | |
| Reward Modeling | PPE Preference ZH | Accuracy82.3 | 19 | |
| Reward Modeling | LMArena-like Benchmarks PPE Pref ZH, In-House QA, In-House Writing v1.0 | PPE Pref ZH Score82.3 | 18 | |
| Reward Modeling | RewardBench v2 | Accuracy90.7 | 14 |