Lexical frequency is a stronger predictor of metaphor novelty than LM surprisal, with the surprisal-novelty link peaking early in training before declining as surprisal becomes more aligned with frequency.
The Inverse Scaling Effect of Pre-Trained Language Model Surprisal Is Not Due to Data Leakage
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Frequency Confound in Language-Model Surprisal and Metaphor Novelty
Lexical frequency is a stronger predictor of metaphor novelty than LM surprisal, with the surprisal-novelty link peaking early in training before declining as surprisal becomes more aligned with frequency.