Contrastive Prefence Learning: Learning from Human Feedback without RL
Paper
•
2310.13639
•
Published
•
25
Human Feedback
-
-
RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
Paper • 2309.00267 • Published • 49 -
Diffusion Model Alignment Using Direct Preference Optimization
Paper • 2311.12908 • Published • 50 -
RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback
Paper • 2312.00849 • Published • 12 -
Direct Language Model Alignment from Online AI Feedback
Paper • 2402.04792 • Published • 32