When an LLM is apprehensive about its answers -- and when its uncertainty is justified Paper • 2503.01688 • Published 6 days ago • 19
LongRoPE2: Near-Lossless LLM Context Window Scaling Paper • 2502.20082 • Published 10 days ago • 31
How to Get Your LLM to Generate Challenging Problems for Evaluation Paper • 2502.14678 • Published 17 days ago • 16
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers Paper • 2502.15007 • Published 17 days ago • 160
The Ultimate Collection of Code Classifiers Collection 🔥 15 classifiers, 124M parameters, one per programming language— for assessing the educational value of GitHub code • 15 items • Updated 17 days ago • 10
You Do Not Fully Utilize Transformer's Representation Capacity Paper • 2502.09245 • Published 24 days ago • 34
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity Paper • 2502.13063 • Published 19 days ago • 65