PAFO: Pareto Fairness Optimization for Personalized Reward Modeling

Computer Science > Artificial Intelligence [Submitted on 6 Jun 2026] PAFO: Pareto Fairness Optimization for Personalized Reward Modeling Xiaoyan Zhao, Haoting Ni, Yang Zhang, Chunyuan Zheng, Haoxuan Li, Fuli Feng 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. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.07988 [cs.AI]   (or arXiv:2606.07988v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.07988 Focus to learn more Submission history From: Xiaoyan Zhao [view email] [v1] Sat, 6 Jun 2026 05:35:31 UTC (1,969 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)