Subword models struggle with word learning, but surprisal hides it Paper • 2502.12835 • Published 10 days ago
German BabyLM Collection Data that can be used for developing developmentally plausible language models in German. • 4 items • Updated 7 days ago
Small Language Models Also Work With Small Vocabularies Collection Models and evaluation data for our 2025 COLING paper (https://aclanthology.org/2025.coling-main.404/). • 10 items • Updated Jan 27