Select Before Use: On the Importance of Reference Model Selection in Preference Alignment.
Muyang Li, Runze Wu, Xiangyu Zhao, Bo Han, Daoyi Dong, Tongliang Liu
Browse the full ACL paper archive.
Muyang Li, Runze Wu, Xiangyu Zhao, Bo Han, Daoyi Dong, Tongliang Liu
Browse the full ACL paper archive.