Training language models to follow instructions with human feedback
Paper
•
2203.02155
•
Published
•
16
Alignment Algorithm Papers
Note RLHF
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Paper • 2305.18290 • Published • 48Note DPO, Stanford, Chelsea Finn's Team
Statistical Rejection Sampling Improves Preference Optimization
Paper • 2309.06657 • Published • 13Note Rejection Sampling
SimPO: Simple Preference Optimization with a Reference-Free Reward
Paper • 2405.14734 • Published • 11Note SimPO, Princeton, Prof. Danqi Chen's Team
Weak-to-Strong Extrapolation Expedites Alignment
Paper • 2404.16792 • Published • 11Note ExPO, the authors claimed ExPO doesn't need model training and tuning Could improve ~0.4 point on MT Bench
Self-Instruct: Aligning Language Model with Self Generated Instructions
Paper • 2212.10560 • Published • 8Note Self-Instruct
WizardLM: Empowering Large Language Models to Follow Complex Instructions
Paper • 2304.12244 • Published • 13Note Evol-Instruct