Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure

원문 초록

Single-axis mitigations of reward-model biases, such as reducing proxy reliance on length, sycophancy, or style, can redirect optimization pressure onto correlated proxies rather than eliminate it, a new type of reward hacking we call reward bias substitution. The failure is enabled by a measurement-versus-optimization gap between mitigation evaluation on the audit distribution and policy training on the policy-induced distribution. Prior reward-hacking analyses assume a fixed reward proxy, whereas we study the mitigation operator that removes one bias from it, the basic step of iterative reward refinement. We formalize mitigation outcomes into a regime taxonomy and prove that successful mitigation, bias substitution, and overcorrection can produce identical observables under every audit-distribution score, including ranking accuracy and win-rate, even when granted oracle access to the true reward. Across 30 published preference-learning mitigation works, no method we survey reports the evidence needed to certify successful mitigation. Augmenting evaluation with policy-induced distributions while tracking multiple biases provably resolves this distributional gap, and we translate this into actionable prescriptions for mitigation methods and benchmarks. We demonstrate bias substitution in RLHF, where a length penalty in GRPO shortens responses as intended yet makes the policy overconfident and less accurate on open-ended questions, show that the same distributional gap hides failures of published mitigations, and find the necessary preconditions for reward bias substitution documented in published results and in our study of length-sycophancy coupling in LLM responses.