Impact of CHARM Calibration on Reward Model Correlation with Human Preferences for Qwen2.5 Variants on Chatbot Arena

Reward models (RMs) play a crucial role in Reinforcement Learning from Human Feedback by serving as proxies for human preferences in aligning large language models. However, they suffer from various biases which could lead to reward hacking. In this paper, we identify a model preference bias in RMs, where they systematically assign disproportionately high scores to responses from certain policy models, leading to unfair judgments. To mitigate this bias, we propose a calibration method named CHatbot Arena calibrated Reward Modeling (CHARM) that leverages Elo scores from the Chatbot Arena to con

Research goal: How does the CHARM calibration method affect the correlation between reward model scores and human preference judgments on the Chatbot Arena leaderboard for Qwen2.5 variants?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.3/10.