In-context learning biases hidden representations toward low-frequency eigenvectors of a reweighted graph Laplacian, a phenomenon the authors prove and test.
A.1 E VENTS IN A RANDOM WALK SEQUENCE Theorem 3 (Theorem 1 in (Fan et al., 2021))
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Provable Low-Frequency Bias of In-Context Learning of Representations
In-context learning biases hidden representations toward low-frequency eigenvectors of a reweighted graph Laplacian, a phenomenon the authors prove and test.