mlsanityData to 7 Oct 2026

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

arXiv 2601.08430 ↗First posted 13 Jan 2026cs.AIcited by 42

Not on the map. Why?

Abstract (arXiv)

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 (~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 hrefhttps://github.com/teqkilla/RubricHub this URL.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Builds on 18 of its 97 references that are in the map. First posted on arXiv 13 Jan 2026.

Builds on

18 of 97 references.

References · 18

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  5. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
  6. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,442
  7. 2023Large Language Models are not Fair Evaluatorscited by 1,050
  8. 2024WildChat: 1M ChatGPT Interaction Logs in the Wildcited by 598
  9. 2024From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipelinecited by 484
  10. 2025Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domainscited by 328
  11. 2025Generalizing Verifiable Instruction Followingcited by 178
  12. 2024LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMscited by 142
6 more
  1. 2025OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignmentcited by 118
  2. 2025Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoningcited by 56
  3. 2025Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Trainingcited by 46
  4. 2025ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubricscited by 44
  5. 2025Reverse-Engineered Reasoning for Open-Ended Generationcited by 32
  6. 2025ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judgecited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 42.

42 papers.

Sort:

By area:

  1. 2026Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Trainingcited by 45
  2. 2026Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challengescited by 30
  3. 2026Reward Hacking in Rubric-Based Reinforcement Learningcited by 18
  4. 2026When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarificationcited by 12
  5. 2026Rubric-Guided Self-Distillation: Post-Training Without Rubric Verifierscited by 9
  6. 2026Rethinking Reward Supervision: Rubric-Conditioned Self-Distillationcited by 9
  7. 2026Omni-RRM: Advancing Omni Reward Modeling via Automatic Rubric-Grounded Preference Synthesiscited by 7
  8. 2026EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generationcited by 7
  9. 2026Generating and Refining Dynamic Evaluation Rubrics for LLM-as-a-Judgecited by 7
  10. 2026Qworld: Question-Specific Evaluation Criteria for LLMscited by 6
  11. 2026Visual Preference Optimization with Rubric Rewardscited by 5
  12. 2026From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscapecited by 4
30 more
  1. 2026Mach-Mind-4-Flash Technical Reportcited by 4
  2. 2026C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferencescited by 3
  3. 2026Think-with-Rubrics: From External Evaluator to Internal Reasoning Guidancecited by 3
  4. 2026RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domainscited by 3
  5. 2026Mitigating False Credit Propagation: Probabilistic Graphical Reward Aggregation for Rubric-Based Reinforcement Learningcited by 3
  6. 2026Reinforcement Learning with Robust Rubric Rewardscited by 2
  7. 2026Rubrics as Privileged Information for Open-Ended Generationcited by 2
  8. 2026Overview of the NLPCC 2026 Shared Task 11: Agent-Based Experiment Reproduction from Scientific Paperscited by 2
  9. 2026DRACULA: Hunting for the Actions Users Want Deep Research Agents to Executecited by 1
  10. 2026AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignmentcited by 1
  11. 2026AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignmentcited by 1
  12. 2026Benchmarking Frontier LLMs on Arabic Cultural and Sociolinguistic Knowledge: A Cross-Evaluation Framework with Human SME Ground Truthcited by 1
  13. 2026FinProBench: Evaluating Financial AI Agents with Role-Grounded Rubrics Derived from Professional Deliverablescited by 1
  14. 2026REVEAL: A Rubric-Guided Agent for Explicit Evidence Sufficiency Verificationin Long-Video Question Answeringcited by 1
  15. 2026Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signalscited by 0
  16. 2026Rubrics on Trial: Evolving Rubrics from a Single Query via Synthetic Pairwise Evidencecited by 0
  17. 2026CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tuning Datacited by 0
  18. 2026CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimizationcited by 0
  19. 2026SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learningcited by 0
  20. 2026APTER: Adaptive Post-Training with Expert-Grounded Rubricscited by 0
  21. 2026RecurSE: Bounded Recursive Self-Evaluation for LLM Rubric Judgescited by 0
  22. 2026RubricRM: Generative Reward Modeling via Dynamic Rubrics for Image Generation and Editingcited by 0
  23. 2026PaperGym: Rubric-Centered Evolution for Research-Plan Generationcited by 0
  24. 2026From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mixcited by 0
  25. 2026RLVR2: Reinforcement Learning with Verifiable Rubric-based Rankingcited by 0
  26. 2026Rubric Rewards from Item Response Theorycited by 0
  27. 2026STAR-GRPO: Canonical Anchoring and Reliability-First Advantages against Representation-Dependent Reward Hackingcited by 0
  28. 2026Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubricscited by 0
  29. 2026Agentic Tool-Augmented Reasoning for Explainable Image Forgery Detectioncited by 0
  30. 2026RewardWeaver: Long-Horizon Interactive Learning for Language Agents via Self-Evolving Reward Adaptationcited by 0