RubricHub: A Comprehensive and Highly Discriminative Rubric Dataset via Automated Coarse-to-Fine Generation

TL;DR

RubricHub introduces a large, multi-domain rubric dataset generated through an automated coarse-to-fine process, significantly improving the performance of reinforcement learning models in reasoning tasks.

Contribution

The paper presents a novel automated rubric generation framework and a large-scale dataset, enabling enhanced supervision for reasoning-intensive open-ended generation tasks.

Findings

RubricHub dataset contains approximately 110,000 examples across multiple domains.

Post-training with RubricHub improves model performance, achieving SOTA results on HealthBench.

The approach surpasses proprietary models like GPT-5 in specific reasoning benchmarks.

Abstract

Reinforcement Learning with Verifiable Rewards (RLVR) has driven substantial progress in reasoning-intensive domains like mathematics. However, optimizing open-ended generation remains challenging due to the lack of ground truth. While rubric-based evaluation offers a structured proxy for verification, existing methods suffer from scalability bottlenecks and coarse criteria, resulting in a supervision ceiling effect. To address this, we propose an automated Coarse-to-Fine Rubric Generation framework. By synergizing principle-guided synthesis, multi-model aggregation, and difficulty evolution, our approach produces comprehensive and highly discriminative criteria capable of capturing the subtle nuances. Based on this framework, we introduce RubricHub, a large-scale ($\sim$110k) and multi-domain dataset. We validate its utility through a two-stage post-training pipeline comprising Rubric-based Rejection Sampling Fine-Tuning (RuFT) and Reinforcement Learning (RuRL). Experimental results demonstrate that RubricHub unlocks significant performance gains: our post-trained Qwen3-14B achieves state-of-the-art (SOTA) results on HealthBench (69.3), surpassing proprietary frontier models such as GPT-5. Our code is available at \href{https://github.com/teqkilla/RubricHub}{ this URL}.