Improving Generalization of Alignment with Human Preferences through Group Invariant Learning
preprint, 2023
Publications
Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback
EMNLP 2023 findings, 2023
Secrets of rlhf in large language models part i: Ppo
Instruction Workshop @ NeurIPS 2023, 2023