One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models

Abstract

Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences. However, RM-based preference-tuning is vulnerable to reward hacking, whereby LM policies learn undesirable behaviors from flawed RMs. By systematically measuring biases in five high-quality RMs, including the state-of-the-art, we find that issues persist despite prior work with respect to length, sycophancy, and overconfidence. We also discover new issues related to bias toward model-specific ``styles'' and answer-order. We categorize RM failures as tractable or resistant to linear intervention and propose a simple post-hoc intervention to mitigate low-complexity biases that arise from spurious correlations. Our proposed mechanistic reward shaping reduces targeted biases without degrading reward quality and while using minimal labeled data. The method is extensible to new biases, model-internal, and generalizes out-of-distribution.