PAFO: Pareto Fairness Optimization for Personalized Reward Modeling

Abstract

Large language models (LLMs) increasingly rely on reward models to align their outputs with diverse user preferences. While personalized reward models aim to capture such heterogeneity, they are often trained on imbalanced user preference data and may therefore favor users whose preferences are more common in the training population. In this paper, we identify this failure mode as personalized reward bias, where reward modeling quality varies systematically with preference support rate. We formulate its mitigation as a Pareto fairness problem over group utilities, aiming to improve under-served users without degrading other user groups. To this end, we propose PAFO, a Pareto fairness optimization framework for personalized reward modeling. PAFO first trains group-specialized reward models for majority and minority preference groups, then constructs conditional margin-level supervision to distill their heterogeneous preference boundaries into a single unified model. The resulting model uses group information only during training and requires no explicit group labels at inference time. Experiments on Personal-LLM and DSP show that PAFO improves both minority-group and majority-group accuracy while reducing user-level unfairness across multiple metrics, demonstrating its effectiveness for fairer LLM personalization.