Epistemic uncertainty collapses sharply at grokking in in-context learning transformers, serving as a diagnostic of delayed generalization and linked via a Bayesian linear model to a shared spectral mechanism.
Noam Itzhak Levi, Alon Beck, and Yohai Bar-Sinai
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Bayesian Perspective on the Role of Epistemic Uncertainty for Delayed Generalization in In-Context Learning
Epistemic uncertainty collapses sharply at grokking in in-context learning transformers, serving as a diagnostic of delayed generalization and linked via a Bayesian linear model to a shared spectral mechanism.