%0 Journal Article %T Larger or Smaller Reward Margins to Select Preferences for Alignment? %A Huang, Kexin %A Wu, Junkang %A Chen, Ziqian %A Wang, Xue %A Gao, Jinyang %A Ding, Bolin %A Wu, Jiancan %A He, Xiangnan %A Wang, Xiang %J Computing Research Repository %V 2025 %N 2503 %D 2025-02-25 %~ DeepDyve