Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
arxiv.org · 5,984 words · saved by 1 readers
N/A
Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains Anisha Gunjal Anthony Wang* Elaine Lau Vaskar Nath Bing Liu Sean Hendryx Scale AI anisha.gunjal@scale.com…
saved by
related reading
- Reasoning in General Domains without Verifiersarxiv.org
- [2605.12474] Reward Hacking in Rubric-Based Reinforcement Learningarxiv.org
- Illustrating Reinforcement Learning from Human Feedback (RLHF)huggingface.co
- [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
- State of RL for reasoning LLMs | A. Weersaweers.de
- [2305.18290] Direct Preference Optimization: Your Language Model is Secretly a Reward Modelarxiv.org
- [2504.13837] Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?arxiv.org
- [2607.18966] Measuring Reward-Seeking via Contrastive Belief Updatesarxiv.org
- 2401.10020.pdfarxiv.org
- [2506.19733] Breaking Barriers: Do Reinforcement Post Training Gains Transfer To Unseen Domains?arxiv.org
- Reinforcement learning towards broadly and persistently beneficial modelsalignment.openai.com
- Reinforcement Learning With Verifiable Rewards: How Data and Verifiers Shape RLVRsnorkel.ai