Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards ACL

Haoxiang Wang | Yong Lin | Wei Xiong | Rui Yang | Shizhe Diao | Shuang Qiu | Han Zhao | Tong Zhang |

Semi-Supervised Reward Modeling via Iterative Self-Training F i n d i n g s - E M N L P

Yifei He | Haoxiang Wang | Ziyan Jiang | Alexandros Papangelis | Han Zhao |

Mitigating the Alignment Tax of RLHF EMNLP

Yong Lin | Hangyu Lin | Wei Xiong | Shizhe Diao | Jianmeng Liu | Jipeng Zhang | Rui Pan | Haoxiang Wang | Wenbin Hu | Hanning Zhang | Hanze Dong | Renjie Pi | Han Zhao | Nan Jiang | Heng Ji | Yuan Yao | Tong Zhang |

Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts F i n d i n g s - E M N L P

Haoxiang Wang | Wei Xiong | Tengyang Xie | Han Zhao | Tong Zhang |