# VerChol -- Grammar-First Tokenization for Agglutinative Languages

arXiv: https://arxiv.org/abs/2603.05883 · HTML: https://mlsanity.com/paper/2603.05883/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 2 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 1 of 1)

- [Less Is More: Reducing Token Counts Without Compromising Performance](https://mlsanity.com/paper/2506.15138/) (2025)

## Abstract (arXiv)

Tokenization is the foundational step in all large language model (LLM) pipelines, yet the dominant approach Byte Pair Encoding (BPE) and its variants is inherently script agnostic and optimized for English like morphology. For agglutinative languages a typological class encompassing the Dravidian family (Tamil, Kannada, Telugu, Malayalam), Turkic languages (Turkish, Azerbaijani, Uzbek), Uralic languages (Finnish, Hungarian, Estonian), Korean, Japanese, Swahili, Basque, and others, a single word may encode root, tense, aspect, person, number, gender agreement, case, and postpositions into one orthographic unit. Statistical tokenizers fragment these words into byte pair chunks that sever morpheme boundaries and inflate token counts.