When an LLM is apprehensive about its answers -- and when its uncertainty is justified Paper • 2503.01688 • Published 7 days ago • 19
When an LLM is apprehensive about its answers -- and when its uncertainty is justified Paper • 2503.01688 • Published 7 days ago • 19 • 2
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach Paper • 2502.05171 • Published about 1 month ago • 122
SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators Paper • 2502.06394 • Published 28 days ago • 86