During pretraining, language models exhibit natural ungrokking where learned rules are forgotten based on their support frequency in the corpus, with asymmetric editability of rule survival.
author Garrette, D
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
A framework using language models to simulate non-existent experiments and derive novel testable hypotheses on dative verb acquisition and cross-structural generalization in children.
Emergent abilities are capabilities present in large language models but absent in smaller ones and cannot be predicted by extrapolating smaller model performance.
citing papers explorer
-
A systematic framework for generating novel experimental hypotheses from language models
A framework using language models to simulate non-existent experiments and derive novel testable hypotheses on dative verb acquisition and cross-structural generalization in children.
-
Emergent Abilities of Large Language Models
Emergent abilities are capabilities present in large language models but absent in smaller ones and cannot be predicted by extrapolating smaller model performance.