Inconsistent Tokenizations Cause Language Models to be Perplexed by Japanese Grammar

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gambardella, Andrew, Kojima, Takeshi, Iwasawa, Yusuke, Matsuo, Yutaka
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2505.19599