#интерпретируемость
-
The Canonical Basis: How to Rotate an LLM to Look Inside It
A researcher has proposed a reversible change of coordinates for the transformer that leaves its behavior untouched but makes every hidden axis individually measurable and controllable.
-
AI's Latent Reasoning Turns Out to Be More Legible Than Thought
Researchers at COLM 2026 showed that models with hidden reasoning either barely use it or conceal perfectly readable mathematical steps inside.