GPDPO: Learning from Reward Conflicts via Group Pareto-Dominance Policy Optimization
Multi-reward reinforcement learning offers a promising framework for aligning large language models (LLMs) with diverse objectives, but conflicting reward signals can induce ambiguous update directions and hinder stable optimization. Existing approaches address such conflicts through reward reweighting, gradient coordi...
Zi-Xuan Xu, Hao-Xuan Chen, Jiang-Xin Sun et al.
· 1 citation