Perturbing prefixes to semantic neighbors during training creates a hierarchical noise model that improves language model predictions on token sequences outside the training corpus support.
M ix CE : Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies
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
-
Perturbation is All You Need for Extrapolating Language Models
Perturbing prefixes to semantic neighbors during training creates a hierarchical noise model that improves language model predictions on token sequences outside the training corpus support.