RaR-Medicine-20k-o3-mini

Anisha Gunjal, Anthony Wang, Elaine Lau, Vaskar Nath, Yunzhong He, Bing Liu, Sean Hendryx

Type: dataset
Venue: HuggingFace (anisha2102)
Year: 2026
Source: huggingface
Access: free
Language: English
Added: 2026-07-17T20:18:03.706305+00:00
Verified: 2026-07-17T20:18:03.706305+00:00

Summary

RaR-Medicine-20k-o3-mini is a dataset of ~22.4k medical questions (17.9k train / 2.24k val / 2.24k test) each paired with a reference answer and checklist-style rubric criteria generated by OpenAI's o3-mini model. It is released as part of the 'Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains' paper (arXiv:2507.17746) to enable structured, multi-criteria reward supervision for RL training of language models on medical reasoning tasks.

Keywords

rubrics reinforcement-learning medicine reasoning rewards o3-mini rlvr

Topics

Medicine / Reasoning

Research notes

Part of the Rubrics as Rewards (RaR) framework. Source questions appear to come from FreedomIntelligence/medical-1-reasoning-SFT and similar medical QA datasets. Rubrics generated by o3-mini.