Search Results for author:
Found 5 papers, 2 papers with code
Different Tokenization Schemes Lead to Comparable Performance in Spanish Number Agreement
The relationship between language model tokenization and performance is an open area of research.
A Bit of a Problem: Measurement Disparities in Dataset Sizes Across Languages
We release a tool to obtain byte premiums for any two languages, enabling comparisons of dataset sizes across languages for more equitable multilingual model development and data practices.
Structural Priming Demonstrates Abstract Grammatical Representations in Multilingual Language Models
We measure crosslingual structural priming in large language models, comparing model behavior to human experimental results from eight crosslingual experiments covering six languages, and four monolingual structural priming experiments in three non-English languages.
When Is Multilinguality a Curse? Language Modeling for 250 High- and Low-Resource Languages
However, concrete evidence for the effects of multilinguality on language modeling performance in individual languages remains scarce.
Crosslingual Structural Priming and the Pre-Training Dynamics of Bilingual Language Models
Do multilingual language models share abstract grammatical representations across languages, and if so, when do these develop?
