Showing 2026 · cs.AIShow all
2 papers · 2 filters
cs.AI2026
Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization
Mohammad Beigi, Ming Jin, Lifu Huang
Reward hacking is usually studied after it becomes visible, once a model earns high proxy reward while failing the intended task. We instead study what proxy RL teaches before that…
cs.AI2026
Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking
Mohammad Beigi, Ming Jin, Junshan Zhang +2
Reinforcement Learning from Human Feedback (RLHF) remains vulnerable to reward hacking, where models exploit spurious correlations in learned reward models to achieve high scores w…