Elamur Research⌕
☰
home / papers / 2026 / OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment

OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment

Paper · 2026 · Tianci Liu, Ran Xu, Tony Yu et al.

Summary

Reward models for RLHF usually output a single score or a pairwise verdict. These signals miss the many dimensions of human preference, especially in subjective tasks where correctness cannot be checked automatically. Rubric-based rewards can help, but rubrics written by experts are costly, and rubrics produced by prompting commercial LLMs are expensive and poorly controlled. The authors release OpenRubrics, a large set of (prompt, rubric) pairs built from public preference and SFT data in general, scientific and medical domains. Their Contrastive Rubric Generation (CRG) method shows an LLM a prompt together with a preferred and a rejected response. The model then writes two kinds of criteria: hard rules, which are explicit constraints from the prompt, and principles, which are implicit qualities of good answers. Rubrics are kept only if they lead to the correct preference label. The resulting reward model, Rubric-RM, beats size-matched baselines by 8.4% on average across eight benchmarks. It also improves policies trained with DPO. The approach offers interpretable, cheaper and scalable reward signals.

Key points

  • Data sources: UltraFeedback, Magpie, Skywork-Preference, Synthetic-IF, MegaScience and Medical-o1.
    • Preference pairs come from score extremes or verification functions.
    • For MegaScience and Medical-o1, an ensemble of Athene-RM-8B and Skywork-Reward-V2-Llama-3.1-8B-40M ranks the responses.
    • A figure suggests the collection holds about 35.7k items.
  • Architecture: Rubric-RM has two Qwen-3-8B parts, a rubric generator and a judge. Both models and the datasets are published at huggingface.co/OpenRubrics.
  • HealthBench reward modeling:
    • Rubric-RM scores 68.3, compared with 63.3 for RRM-7B.
    • Majority voting raises this to 72.9.
    • Prompting Qwen-3-8B directly with a rubric-plus-judge pipeline reaches only 51.8.
  • HealthBench DPO:
    • Training Qwen-2.5-7B-Instruct with Rubric-RM as the judge lifts its score from 21.6 to 23.8.
    • ArmoRM reaches 22.5 and RM-R1-7B reaches 22.7.
  • Efficiency and case study:
    • Rubric-RM processes 100 RewardBench2 samples in 130.77 s, compared with 203.4 s for RRM-7B. Rubrics can be cached for reuse.
    • In a case study, checking hard rules first stopped the model from preferring an overly long response that broke the prompt's constraint.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Georgia Institute of TechnologyAtlanta · United States133 works · 24,497 citations🎓Emory UniversityAtlanta · United States36 works · 39,779 citations🎓Purdue University West LafayetteWest Lafayette · United States23 works · 1,417 citations🎓University at Albany, State University of New YorkAlbany · United States5 works · 83 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,320 works

Cite

Cite as Tianci Liu, Ran Xu, Tony Yu, Ilgee Hong, Carl Yang, Tuo Zhao and Haoyu Wang. 2026. OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.791

@inproceedings{liu2026openrubrics,
  title = {{OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment}},
  author = {Tianci Liu, Ran Xu, Tony Yu, Ilgee Hong, Carl Yang, Tuo Zhao and Haoyu Wang},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.791},
  url = {https://doi.org/10.18653/v1/2026.acl-long.791}
}

References

61 references, 27 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Kaikai An, Li Sheng, Ganqu Cui, Shuzheng Si, Ning Ding, Yu Cheng, and Baobao Chang. 2025. UltraIF: Advancing instruction following from the wild. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 18711–18726, Suzhou, China. Association for Computational…
  2. Zachary Ankner, Mansheej Paul, Brandon Cui, Jonathan D Chang, and Prithviraj Ammanabrolu. 2024. Critique-out-loud reward models. arXiv preprint arXiv:2408.11791. find
  3. Rahul K Arora, Jason Wei, Rebecca Soskin Hicks, Preston Bowman, Joaquin Quiñonero-Candela, Foivos Tsimpourlas, Michael Sharman, Meghan Shah, Andrea Vallone, Alex Beutel, and 1 others. 2025. Healthbench: Evaluating large language models towards improved human health. arXiv preprint arXiv:2505.08775.
  4. Adithya Bhaskar, Xi Ye, and Danqi Chen. 2025. Language models that think, chat better. arXiv preprint arXiv:2509.20357. find
  5. Ralph Allan Bradley and Milton E Terry. 1952. Rank analysis of incomplete block designs: I. the method of paired comparisons. Biometrika, 39(3/4):324– 345. find
  6. Junying Chen, Zhenyang Cai, Ke Ji, Xidong Wang, Wanlong Liu, Rongsheng Wang, Jianye Hou, and Benyou Wang. 2024. Huatuogpt-o1, towards medical complex reasoning with llms. arXiv preprint arXiv:2412.18925. find
  7. Nuo Chen, Zhiyuan Hu, Qingyun Zou, Jiaying Wu, Qian Wang, Bryan Hooi, and Bingsheng He. 2025. Judgelrm: Large reasoning models as a judge. arXiv preprint arXiv:2504.00050. — [arXiv:2504.00050](https://arxiv.org/abs/2504.00050) find
  8. Xiusi Chen, Gaotang Li, Ziqi Wang, Bowen Jin, Cheng Qian, Yu Wang, Hongru WANG, Yu Zhang, Denghui Zhang, Tong Zhang, Hanghang Tong, and Heng Ji. 2026. RM-r1: Reward modeling as reasoning. In The Fourteenth International Conference on Learning Representations.
  9. Wei-Lin Chiang, Zhuohan Li, Ziqing Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E Gonzalez, and 1 others. 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. find
  10. Ganqu Cui, Lifan Yuan, Ning Ding, Guanming Yao, Bingxiang He, Wei Zhu, Yuan Ni, Guotong Xie, Ruobing Xie, Yankai Lin, Zhiyuan Liu, and Maosong Sun. 2024. ULTRAFEEDBACK: Boosting language models with scaled AI feedback. In Forty-first International Conference on Machine Learning. find
  11. Ning Ding, Yulin Chen, Bokai Xu, Yujia Qin, Shengding Hu, Zhiyuan Liu, Maosong Sun, and Bowen Zhou. 2023. Enhancing chat language models by scaling high-quality instructional conversations. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 3029–3051, Si…
  12. Guanting Dong, Keming Lu, Chengpeng Li, Tingyu Xia, Bowen Yu, Chang Zhou, and Jingren Zhou. 2024. Self-play with execution feedback: Improving instruction-following capabilities of large language models. arXiv preprint arXiv:2406.13542. find
  13. Run-Ze Fan, Zengzhi Wang, and Pengfei Liu. 2025. Megascience: Pushing the frontiers of post-training datasets for science reasoning. arXiv preprint arXiv:2507.16812. — [arXiv:2507.16812](https://arxiv.org/abs/2507.16812) find
  14. Evan Frick, Peter Jin, Tianle Li, Karthik Ganesan, Jian Zhang, Jiantao Jiao, and Banghua Zhu. 2024a. Athene-70b: Redefining the boundaries of post-training for open models. find
  15. Evan Frick, Tianle Li, Connor Chen, Wei-Lin Chiang, Anastasios N. Angelopoulos, Jiantao Jiao, Banghua Zhu, Joseph E. Gonzalez, and Ion Stoica. 2024b. How to evaluate reward models for rlhf. Preprint, arXiv:2410.14872. find
  16. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, and 1 others. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783.
  17. Anisha Gunjal, Anthony Wang, Elaine Lau, Vaskar Nath, Yunzhong He, Bing Liu, and Sean M. Hendryx. 2026. Rubrics as rewards: Reinforcement learning beyond verifiable domains. In The Fourteenth International Conference on Learning Representations. find
  18. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, and 1 others. 2025a. Deepseekr1 incentivizes reasoning in llms through reinforcement learning. Nature, 645(8081):633–638. find
  19. Jiaxin Guo, Zewen Chi, Li Dong, Qingxiu Dong, Xun Wu, Shaohan Huang, and Furu Wei. 2025b. Reward reasoning models. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. find
  20. Yifu Guo, Jiaye Lin, Huacan Wang, Yuzhen Han, Sen Hu, Ziyi Ni, Licheng Wang, and Mingguang Chen. 2025c. SE-agent: Self-evolution trajectory optimization in multi-step reasoning with LLM-based agents. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. find
  21. Helia Hashemi, Jason Eisner, Corby Rosset, Benjamin Van Durme, and Chris Kedzie. 2024. LLM-rubric: A multidimensional, calibrated approach to automated evaluation of natural language texts. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pap…
  22. Zenan Huang, Yihong Zhuang, Guoshan Lu, Zeyu Qin, Haokai Xu, Tianyu Zhao, Ru Peng, Jiaqi Hu, Zhanming Shen, Xiaomeng Hu, and 1 others. 2025. Reinforcement learning with rubric anchors. arXiv preprint arXiv:2508.12790. — [arXiv:2508.12790](https://arxiv.org/abs/2508.12790) find
  23. Yuxin Jiang, Yufei Wang, Xingshan Zeng, Wanjun Zhong, Liangyou Li, Fei Mi, Lifeng Shang, Xin Jiang, Qun Liu, and Wei Wang. 2024. Follow-Bench: A multi-level fine-grained constraints following benchmark for large language models. In Proceedings of the 62nd Annual Meeting of the Association for Comput… find
  24. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient memory management for large language model serving with pagedattention. In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles.
  25. Nathan Lambert, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James V Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, and 1 others. 2024. Tulu 3: Pushing frontiers in open language model post-training. arXiv preprint arXiv:2411.15124.
  26. Nathan Lambert, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James Validad Miranda, Alisa Liu, Nouha Dziri, Xinxi Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D. Hwang, Jiangjiang Yang, Ronan Le Bras, Oyvind Tafjord, Christopher Wilhelm, Luca Soldaini,… — Tulu 3: Pushing Frontiers in Open Language Model Post-Training
  27. Nathan Lambert, Valentina Pyatkin, Jacob Morrison, LJ Miranda, Bill Yuchen Lin, Khyathi Chandu, Nouha Dziri, Sachin Kumar, Tom Zick, Yejin Choi, Noah A. Smith, and Hannaneh Hajishirzi. 2025b. RewardBench: Evaluating reward models for language modeling. In Findings of the Association for Computationa… find
  28. Mengdi Li, Jiaye Lin, Xufeng Zhao, Wenhao Lu, Peilin Zhao, Stefan Wermter, and Di Wang. 2025. Curriculum-rlaif: Curriculum alignment with reinforcement learning from ai feedback. arXiv preprint arXiv:2505.20075. find
  29. Bill Yuchen Lin, Yuntian Deng, Khyathi Chandu, Abhilasha Ravichander, Valentina Pyatkin, Nouha Dziri, Ronan Le Bras, and Yejin Choi. 2025. Wildbench: Benchmarking LLMs with challenging tasks from real users in the wild. In The Thirteenth International Conference on Learning Representations.
  30. Stephanie Lin, Jacob Hilton, and Owain Evans. 2022. TruthfulQA: Measuring how models mimic human falsehoods. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3214–3252, Dublin, Ireland. Association for Computational Linguistics…
  31. Chris Yuhao Liu, Liang Zeng, Jiacai Liu, Rui Yan, Jujie He, Chaojie Wang, Shuicheng Yan, Yang Liu, and Yahui Zhou. 2024. Skywork-reward: Bag of tricks for reward modeling in llms. arXiv preprint arXiv:2410.18451.
  32. Chris Yuhao Liu, Liang Zeng, Yuzhen Xiao, Jujie He, Jiacai Liu, Chaojie Wang, Rui Yan, Wei Shen, Fuxiang Zhang, Jiacheng Xu, and 1 others. 2025a. Skywork-reward-v2: Scaling preference data curation via human-ai synergy. arXiv preprint arXiv:2507.01352.
  33. Yantao Liu, Zijun Yao, Rui Min, Yixin Cao, Lei Hou, and Juanzi Li. 2025b. Pairjudge rm: Perform best-of-n sampling with knockout tournament. arXiv preprint arXiv:2501.13007. — [arXiv:2501.13007](https://arxiv.org/abs/2501.13007) find
  34. EMNLP 2024, pages 1043–1067, Miami, Florida, USA. Association for Computational Linguistics. find
  35. Aditya Pathak, Rachit Gandhi, Vaibhav Uttam, Arnav Ramamoorthy, Pratyush Ghosh, Aaryan Raj Jindal, Shreyash Verma, Aditya Mittal, Aashna Ased, Chirag Khatri, and 1 others. 2025. Rubric is all you need: Improving llm-based code evaluation with question-specific rubrics. In Proceedings of the 2025 ACM… find
  36. Hao Peng, Yunjia Qi, Xiaozhi Wang, Zijun Yao, Bin Xu, Lei Hou, and Juanzi Li. 2025. Agentic reward modeling: Integrating human preferences with verifiable correctness signals for reliable reward systems. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volu…
  37. Yiwei Qin, Kaiqiang Song, Yebowen Hu, Wenlin Yao, Sangwoo Cho, Xiaoyang Wang, Xuansheng Wu, Fei Liu, Pengfei Liu, and Dong Yu. 2024. InFoBench: Evaluating instruction following ability in large language models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 13025– 1304…
  38. Yantao Liu, Zijun Yao, Rui Min, Yixin Cao, Lei Hou, and Juanzi Li. 2025c. RM-bench: Benchmarking reward models of language models with subtlety and style. In The Thirteenth International Conference on Learning Representations.
  39. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, and 1 others. 2025. Gemma 3 technical report. arXiv preprint arXiv:2503.19786. find
  40. Saumya Malik, Valentina Pyatkin, Sander Land, Jacob Morrison, Noah A Smith, Hannaneh Hajishirzi, and Nathan Lambert. 2025. Rewardbench 2: Advancing reward model evaluation. arXiv preprint arXiv:2506.01937. — [arXiv:2506.01937](https://arxiv.org/abs/2506.01937) find
  41. Vijay Viswanathan, Yanchao Sun, Xiang Kong, Meng Cao, Graham Neubig, and Tongshuang Wu. 2025. Checklists are better than reward models for aligning language models. In The Thirty-ninth Annual Conference on Neural Information Processing Systems.
  42. Tong Mu, Alec Helyar, Johannes Heidecke, Joshua Achiam, Andrea Vallone, Ian D Kivlichan, Molly Lin, Alex Beutel, John Schulman, and Lilian Weng. 2024. Rule based rewards for language model safety. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. find
  43. Yifan Wang, Bolian Li, Junlin Wu, Zhaoxuan Tan, Zheli Liu, Ruqi Zhang, Ananth Grama, and Qingkai Zeng. 2025. Drift: Learning from abundant user dissatisfaction in real-world preference learning. arXiv preprint arXiv:2510.02341. — [arXiv:2510.02341](https://arxiv.org/abs/2510.02341) find
  44. Shuaiyi Nie, Siyu Ding, Wenyuan Zhang, Linhao Yu, Tianmeng Yang, Yao Chen, Tingwen Liu, Weichong Yin, Yu Sun, and Hua Wu. 2026. Attnpo: Attention-guided process supervision for efficient reasoning. arXiv preprint arXiv:2602.09953.
  45. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, and 1 others. 2022. Training language models to follow instructions with human feedback. Advances in neural information processing systems, 35:27730–27744.
  46. Junsoo Park, Seungyeon Jwa, Ren Meiying, Daeyoung Kim, and Sanghyuk Choi. 2024. OffsetBias: Leveraging debiased data for tuning evaluators. In Findings of the Association for Computational Linguistics: Zhilin Wang, Yi Dong, Olivier Delalleau, Jiaqi Zeng, Gerald Shen, Daniel Egert, Jimmy J. Zhang, Ma…
  47. Xumeng Wen, Zihan Liu, Shun Zheng, Shengyu Ye, Zhirong Wu, Yang Wang, Zhijian Xu, Xiao Liang, Junjie Li, Ziming Miao, and 1 others. 2025. Reinforcement learning with verifiable rewards implicitly incentivizes correct reasoning in base llms. arXiv preprint arXiv:2506.14245. find
  48. Chenxi Whitehouse, Tianlu Wang, Ping Yu, Xian Li, Jason E Weston, Ilia Kulikov, and Swarnadeep Saha. 2026. J1: Incentivizing thinking in LLM-as-a-judge via reinforcement learning. In The Fourteenth International Conference on Learning Representations. find
  49. Zeqiu Wu, Yushi Hu, Weijia Shi, Nouha Dziri, Alane Suhr, Prithviraj Ammanabrolu, Noah A Smith, Mari Ostendorf, and Hannaneh Hajishirzi. 2023. Fine-grained human feedback gives better rewards for language model training. Advances in Neural Information Processing Systems, 36:59008–59033.
  50. Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, Qingwei Lin, and Daxin Jiang. 2024. WizardLM: Empowering large pre-trained language models to follow complex instructions. In The Twelfth International Conference on Learning Representations.
  51. Ran Xu, Jingjing Chen, Jiayu Ye, Yu Wu, Jun Yan, Carl Yang, and Hongkun Yu. 2026a. Incentivizing agentic reasoning in llm judges via tool-integrated reinforcement learning. In The Fourteenth International Conference on Learning Representations. find
  52. Ran Xu, Tianci Liu, Zihan Dong, Tony Yu, Ilgee Hong, Carl Yang, Linjun Zhang, Tao Zhao, and Haoyu Wang. 2026b. Alternating reinforcement learning for rubric-based reward modeling in non-verifiable llm post-training. Preprint, arXiv:2602.01511. — [arXiv:2602.01511](https://arxiv.org/abs/2602.01511) find
  53. Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, and 1 others. 2025b. Qwen3 embedding: Advancing text embedding and reranking through foundation models. arXiv preprint arXiv:2506.05176.
  54. Yaowei Zheng, Richong Zhang, Junhao Zhang, Yanhan Ye, Zheyan Luo, Zhangchi Feng, and Yongqiang Ma. 2024. Llamafactory: Unified efficient fine-tuning of 100+ language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations),…
  55. Yang Zhou, Sunzhu Li, Shunyu Liu, Wenkai Fang, Kongcheng Zhang, Jiale Zhao, Jingwen Yang, Yihe Zhou, Jianwei Lv, Tongya Zheng, and 1 others. 2025. Breaking the exploration bottleneck: Rubric-scaffolded reinforcement learning for general llm reasoning. arXiv preprint arXiv:2508.16949. — [arXiv:2508.16949](https://arxiv.org/abs/2508.16949) find
  56. Zhangchen Xu, Fengqing Jiang, Luyao Niu, Yuntian Deng, Radha Poovendran, Yejin Choi, and Bill Yuchen Lin. 2025. Magpie: Alignment data synthesis from scratch by prompting aligned LLMs with nothing. In The Thirteenth International Conference on Learning Representations.
  57. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388.
  58. Yue Yu, Zhengxing Chen, Aston Zhang, Liang Tan, Chenguang Zhu, Richard Yuanzhe Pang, Yundi Qian, Xuewei Wang, Suchin Gururangan, Chao Zhang, Melanie Kambadur, Dhruv Mahajan, and Rui Hou. 2025. Self-generated critiques boost reward modeling for language models. In Proceedings of the 2025 Conference o… find
  59. Junkai Zhang, Zihao Wang, Lin Gui, Swarnashree Mysore Sathyendra, Jaehwan Jeong, Victor Veitch, Wei Wang, Yunzhong He, Bing Liu, and Lifeng Jin. 2026. Chasing the tail: Effective rubric-based reward modeling for large language model post-training. In The Fourteenth International Conference on Learni… find
  60. Lunjun Zhang, Arian Hosseini, Hritik Bansal, Mehran Kazemi, Aviral Kumar, and Rishabh Agarwal. 2025a. Generative verifiers: Reward modeling as next-token prediction. In The Thirteenth International Conference on Learning Representations.
  61. Rubric-Generator Epochs Cutoff Length Batch Size Optimizer Learning Rate LR Schedule Warmup 1 3072 128 AdamW −6 8 × 10 Cosine 0.05 Judge-Generator Epochs Cutoff Length Batch Size Optimizer Learning Rate LR Schedule Warmup 2 6144 64 AdamW −6 5 × 10 / / Epochs Cutoff Length Batch Size Optimizer Learni… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/liu-2026-openrubrics-scalable-synthetic-rubric-generation/