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

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

Research output: Contribution to conferenceConference Paperpeer-review

Original languageEnglish
DOIs
Publication statusPublished - Aug 2024
EventThe 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) -
Duration: 1 Aug 20241 Aug 2024

Conference

ConferenceThe 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024)
Period1/08/241/08/24

Cite this