Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation Paper • 2510.21891 • Published 19 days ago • 2
Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting Paper • 2510.08696 • Published Oct 9 • 13
PILAF: Optimal Human Preference Sampling for Reward Modeling Paper • 2502.04270 • Published Feb 6 • 11
A Tale of Tails: Model Collapse as a Change of Scaling Laws Paper • 2402.07043 • Published Feb 10, 2024 • 16