Efficient RLHF: Reducing the Memory Usage of PPO
Paper • 2309.00754 • Published • 16
RLHF papers
-
-
Statistical Rejection Sampling Improves Preference Optimization
Paper • 2309.06657 • Published • 15 -
Aligning Large Multimodal Models with Factually Augmented RLHF
Paper • 2309.14525 • Published • 32 -
Stabilizing RLHF through Advantage Model and Selective Rehearsal
Paper • 2309.10202 • Published • 11 -
Aligning Language Models with Offline Reinforcement Learning from Human Feedback
Paper • 2308.12050 • Published • 1 -
Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment
Paper • 2310.00212 • Published • 2 -
A Long Way to Go: Investigating Length Correlations in RLHF
Paper • 2310.03716 • Published • 10 -
Large Language Models Cannot Self-Correct Reasoning Yet
Paper • 2310.01798 • Published • 36 -
Enable Language Models to Implicitly Learn Self-Improvement From Data
Paper • 2310.00898 • Published • 24 -
Qwen Technical Report
Paper • 2309.16609 • Published • 38 -
Improving Language Models with Advantage-based Offline Policy Gradients
Paper • 2305.14718 • Published • 2 -
Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
Paper • 2305.03047 • Published • 1