Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zheng, Brian Siyuan, Liu, Alisa, Ahia, Orevaoghene, Hayase, Jonathan, Choi, Yejin, Smith, Noah A.
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2506.19004