PAFO applies Pareto fairness optimization and group-specialized distillation to produce a single personalized reward model that improves accuracy for both majority and minority preference groups without requiring group labels at inference.
Towards large language models that benefit for all: Benchmarking group fairness in reward models.arXiv preprint arXiv:2503.07806, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PAFO: Pareto Fairness Optimization for Personalized Reward Modeling
PAFO applies Pareto fairness optimization and group-specialized distillation to produce a single personalized reward model that improves accuracy for both majority and minority preference groups without requiring group labels at inference.