Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning

Xuekang Wang, Zhuoyuan Hao, Shuo Hou +3

Rubric-based reinforcement learning (RL) uses an LLM-as-a-Judge (LaaJ) to score model outputs according to rubrics as rewards. However, policy models may exploit latent biases in t…