Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders Paper • 2503.03601 • Published 9 days ago • 208
When an LLM is apprehensive about its answers -- and when its uncertainty is justified Paper • 2503.01688 • Published 11 days ago • 19
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach Paper • 2502.05171 • Published Feb 7 • 124
SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators Paper • 2502.06394 • Published Feb 10 • 86