RVPO: Risk-Sensitive Alignment via Variance Regularization
cs.LG, cs.CL
Submitted: 2026-05-07
Updated: 2026-10-27
Comments: 17 pages, 5 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
- Safe RLHF: Safe Reinforcement Learning from Human Feedback
- Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization
- ODIN: Disentangled Reward Mitigates Hacking in RLHF
- Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
- Checklists Are Better Than Reward Models For Aligning Language Models
- Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach
- Multi-objective Large Language Model Alignment with Hierarchical Experts
- Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework
- Reward-free Alignment for Conflicting Objectives
- PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- ToolRL: Reward is All Tool Learning Needs
- Qwen2.5 Technical Report
- HybridFlow: A Flexible and Efficient RLHF Framework
- HealthBench: Evaluating Large Language Models Towards Improved Human Health
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis