Measuring Reasoning Utility in LLMs via Conditional Entropy Reduction Paper • 2508.20395 • Published 10 days ago • 1
SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs Paper • 2502.12134 • Published Feb 17 • 2
SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning Paper • 2505.11484 • Published May 16 • 5
Generative AI for Synthetic Data Generation: Methods, Challenges and the Future Paper • 2403.04190 • Published Mar 7, 2024 • 1