ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models

Abstract

The safety alignment of large language models (LLMs) often relies on reinforcement learning from human feedback (RLHF), which requires human annotations to construct preference datasets. Given the challenge of assigning overall quality scores to data, recent works increasingly adopt fine-grained ratings based on multiple safety rules. In this paper, we discover a robust phenomenon: Rules with higher rating entropy tend to have lower accuracy in distinguishing human-preferred responses. Exploiting this insight, we propose ENCORE, a simple entropy-guided method to compose multi-head rewards by penalizing rules with high rating entropy. Theoretically, we show that such rules yield negligible weights under the Bradley-Terry loss during weight optimization, naturally justifying their penalization. Empirically, ENCORE consistently outperforms strong baselines, including random and uniform weighting, single-head Bradley-Terry, and LLM-as-a-judge, etc. on RewardBench safety tasks. Our method is completely training-free, generally applicable across datasets, and retains interpretability, making it a practical and effective approach for multi-attribute reward modeling.