Summary of Copr: Continual Learning Human Preference Through Optimal Policy Regularization, by Han Zhang et al.
COPR: Continual Learning Human Preference through Optimal Policy Regularizationby Han Zhang, Lin Gui, Yuanzhao Zhai,…
Summary of Mitigating the Alignment Tax Of Rlhf, by Yong Lin et al.
Mitigating the Alignment Tax of RLHFby Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng…