# Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights

arXiv: https://arxiv.org/abs/2506.17789 · HTML: https://mlsanity.com/paper/2506.17789/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 21 Jun 2025.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates](https://mlsanity.com/paper/1804.10959/) (2018)
- [How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models](https://mlsanity.com/paper/2012.15613/) (2020)
- [Language Model Tokenizers Introduce Unfairness Between Languages](https://mlsanity.com/paper/2305.15425/) (2023)
- [Byte Pair Encoding is Suboptimal for Language Model Pretraining](https://mlsanity.com/paper/2004.03720/) (2020)
- [Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages](https://mlsanity.com/paper/2104.05596/) (2021)
- [Tokenizer Choice For LLM Training: Negligible or Crucial?](https://mlsanity.com/paper/2310.08754/) (2023)
- [Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages](https://mlsanity.com/paper/2305.17179/) (2023)
- [Why do language models perform worse for morphologically complex languages?](https://mlsanity.com/paper/2411.14198/) (2024)
- [Tokenization and the Noiseless Channel](https://mlsanity.com/paper/2306.16842/) (2023)
- [Improving Multilingual Models with Language-Clustered Vocabularies](https://mlsanity.com/paper/2010.12777/) (2020)
- [IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languages](https://mlsanity.com/paper/2403.06350/) (2024)
- [Airavata: Introducing Hindi Instruction-tuned LLM](https://mlsanity.com/paper/2401.15006/) (2024)
- [BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training](https://mlsanity.com/paper/2409.04599/) (2024)
- [Scaffold-BPE: Enhancing Byte Pair Encoding for Large Language Models with Simple and Effective Scaffold Token Removal](https://mlsanity.com/paper/2404.17808/) (2024)
- [One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers](https://mlsanity.com/paper/2506.10766/) (2025)
- [Beyond Literal Token Overlap: Token Alignability for Multilinguality](https://mlsanity.com/paper/2502.06468/) (2025)

## Built on by (most cited first, 2 of 2)

- [MUTANT: A Recipe for Multilingual Tokenizer Design](https://mlsanity.com/paper/2511.03237/) (2025)
- [Rethinking Indic AI from a Lens of Cultural Heritage Preservation](https://mlsanity.com/paper/2607.06544/) (2026)

## Abstract (arXiv)

Tokenization plays a pivotal role in NLP and is fundamental to training language models. However, existing tokenizers are often skewed towards high-resource languages, limiting their effectiveness for linguistically diverse and morphologically rich languages such as those in the Indian subcontinent. In this work, we present a comprehensive empirical study of multilingual tokenization across 17 Indic languages spanning 11 scripts and two language families. We systematically evaluate the effects of (i) widely used subword algorithms: BPE and Unigram LM, (ii) script and orthography-aware normalization, (iii) vocabulary size, and (iv) multilingual vocabulary construction strategies. We use a combination of intrinsic and extrinsic evaluations to obtain the following observations: (i) script-specific normalization improves tokenization quality, (ii) Unigram LM better preserves morphological boundaries than BPE, (iii) cluster-based vocabulary construction shows improvement in downstream tasks compared to the joint method. Our findings highlight the importance of linguistically informed design choices in multilingual tokenization and offer practical guidance for building effective tokenizers for low-resource and morphologically complex languages.