This content will become publicly available on October 10, 2026

Title: UTF-8 Plumbing: Byte-level Tokenizers Unavoidably Enable LLMs to Generate Ill-formed UTF-8
Award ID(s):
2313028
PAR ID:
10633745
Author(s) / Creator(s):
; ; ;
Publisher / Repository:
2nd Conference on Language Modeling (COLM 2025)
Date Published:
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)