4 citations · 4 across the 12 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Beyond Prediction: A Component-Level Study of Concept Recovery in In-Context Learning
Xufeng Liu, Fang Wan, Yi Liu
In-context learning (ICL) enables language models to make accurate predictions from demonstrations, but prediction success alone does not reveal the extent to which the underlying…
cs.LG2026
The Spectral Geometry of Thought: Phase Transitions, Instruction Reversal, Token-Level Dynamics, and Perfect Correctness Prediction in How Transformers Reason
Yi Liu
We discover that large language models exhibit \emph{spectral phase transitions} in their hidden activation spaces when engaging in reasoning versus factual recall. Through systema…