Type-Driven Tokenization for Brahmic Scripts
arXiv:2609.22125v1 Announce Type: new Abstract: Standard tokenizers used in large language models produce malformed text when applied to Brahmic scripts. They are a family of abugidas, writing systems whose consonants carry an inherent vowel that dependent marks can modify. They include Devanagari,…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-09-22 04:00 · arXiv cs.CL
Type-Driven Tokenization for Brahmic Scripts