Collection by
Oct 30, 2023
Oct 30, 2023
-
Tuna: Instruction Tuning using Feedback from Large Language Models
Paper • 2310.13385 • Published • 10 -
Contrastive Prefence Learning: Learning from Human Feedback without RL
Paper • 2310.13639 • Published • 24 -
Teaching Language Models to Self-Improve through Interactive Demonstrations
Paper • 2310.13522 • Published • 11 -
Zephyr: Direct Distillation of LM Alignment
Paper • 2310.16944 • Published • 121
