Collection by
Mar 27
Mar 27
-
Self-Taught Self-Correction for Small Language Models
Paper • 2503.08681 • Published • 15 -
Self-Improving Robust Preference Optimization
Paper • 2406.01660 • Published • 20 -
LADDER: Self-Improving LLMs Through Recursive Problem Decomposition
Paper • 2503.00735 • Published • 21 -
Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge
Paper • 2407.19594 • Published • 21
