# To Each Language Its Tokenizer: Modular Tokenizers for Efficient Multilingual LLMs

arXiv: https://arxiv.org/abs/2609.15528 · HTML: https://mlsanity.com/paper/2609.15528/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 44 of its 61 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Builds on (most cited first, 30 of 44)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates](https://mlsanity.com/paper/1804.10959/) (2018)
- [ZeRO-Offload: Democratizing Billion-Scale Model Training](https://mlsanity.com/paper/2101.06840/) (2021)
- [The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants](https://mlsanity.com/paper/2308.16884/) (2023)
- [Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca](https://mlsanity.com/paper/2304.08177/) (2023)
- [Adaptive Input Representations for Neural Language Modeling](https://mlsanity.com/paper/1809.10853/) (2018)
- [Language Model Tokenizers Introduce Unfairness Between Languages](https://mlsanity.com/paper/2305.15425/) (2023)
- [Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models](https://mlsanity.com/paper/2305.13707/) (2023)
- [WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization](https://mlsanity.com/paper/2010.03093/) (2020)
- [FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language](https://mlsanity.com/paper/2506.20920/) (2025)
- [Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities](https://mlsanity.com/paper/2404.17790/) (2024)
- [OLMES: A Standard for Language Model Evaluations](https://mlsanity.com/paper/2406.08446/) (2024)
- [WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models](https://mlsanity.com/paper/2112.06598/) (2021)
- [Tokenization Is More Than Compression](https://mlsanity.com/paper/2402.18376/) (2024)
- [XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models](https://mlsanity.com/paper/2301.10472/) (2023)
- [Efficient softmax approximation for GPUs](https://mlsanity.com/paper/1609.04309/) (2016)
- [Getting the most out of your tokenizer for pre-training and domain adaptation](https://mlsanity.com/paper/2402.01035/) (2024)
- [SuperBPE: Space Travel for Language Models](https://mlsanity.com/paper/2503.13423/) (2025)
- [Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance](https://mlsanity.com/paper/2403.06265/) (2024)
- [Improving Multilingual Models with Language-Clustered Vocabularies](https://mlsanity.com/paper/2010.12777/) (2020)
- [Fast Vocabulary Transfer for Language Model Compression](https://mlsanity.com/paper/2402.09977/) (2024)
- [MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling](https://mlsanity.com/paper/2403.10691/) (2024)
- [A Formal Perspective on Byte-Pair Encoding](https://mlsanity.com/paper/2306.16837/) (2023)

## Abstract (arXiv)

Multilingual Large Language Models (LLMs) traditionally rely on a single vocabulary shared by all supported languages, which can lead to uneven compression across them. Moreover, their large embedding and output matrices increase memory usage and slow inference, notably for small-scale models. It is also wasteful as models are often used for only a subset of languages. To address these issues, we introduce a modular framework for multilingual model training. First, we propose methods to learn large modular BPE and Unigram tokenizers that enable extraction of subtokenizers tailored to any language subset. These subtokenizers achieve compression on par with monolingual tokenizers and improve cross-lingual fairness. Second, we design a pretraining strategy that samples subtokenizers to form batches, restricting predictions to the relevant vocabulary subset and allowing efficient training despite a large vocabulary. This supports efficient inference with any combination of language-specific vocabularies. Therefore, it reduces memory usage and speeds up inference in models without sacrificing performance.