Mitigating Reward Hacking in Reinforcement Learning from Human Feedback via Advantage Sign Robustness
cs.LG, cs.AI, cs.CL
Submitted: 2026-04-03
Updated: 2026-11-07
Terminology
Sources
- Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
- Understanding R1-Zero-Like Training: A Critical Perspective
- RewardBench 2: Advancing Reward Model Evaluation
- On Symmetric Losses for Robust Policy Optimization with Noisy Preferences
- GPT-4 Technical Report
- Qwen2.5 Technical Report
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Fine-Tuning Language Models from Human Preferences
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