UNA: Unifying Alignments of RLHF/PPO, DPO and KTO by a Generalized Implicit Reward Function

Add code
Aug 27, 2024
Figure 1 for UNA: Unifying Alignments of RLHF/PPO, DPO and KTO by a Generalized Implicit Reward Function
Figure 2 for UNA: Unifying Alignments of RLHF/PPO, DPO and KTO by a Generalized Implicit Reward Function
Figure 3 for UNA: Unifying Alignments of RLHF/PPO, DPO and KTO by a Generalized Implicit Reward Function
Figure 4 for UNA: Unifying Alignments of RLHF/PPO, DPO and KTO by a Generalized Implicit Reward Function

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: