-
Calibrating Reasoning in Language Models with Internal Consistency
Paper • 2405.18711 • Published • 1 -
Emergence of a High-Dimensional Abstraction Phase in Language Transformers
Paper • 2405.15471 • Published • 1 -
Not All Language Model Features Are Linear
Paper • 2405.14860 • Published • 33 -
Your Transformer is Secretly Linear
Paper • 2405.12250 • Published • 133
Collections
Discover the best community collections!
Collections including paper arxiv:2404.07129