# How does a Language-Specific Tokenizer affect LLMs?

arXiv: https://arxiv.org/abs/2502.12560 · HTML: https://mlsanity.com/paper/2502.12560/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 18 Feb 2025.

## Builds on (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://mlsanity.com/paper/2204.06745/) (2022)
- [How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models](https://mlsanity.com/paper/2012.15613/) (2020)
- [SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling](https://mlsanity.com/paper/2312.15166/) (2023)
- [Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance](https://mlsanity.com/paper/2403.06265/) (2024)
- [How do different tokenizers perform on downstream tasks in scriptio continua languages?: A case study in Japanese](https://mlsanity.com/paper/2306.09572/) (2023)
- [Modeling Confidence in Sequence-to-Sequence Models](https://mlsanity.com/paper/1910.01859/) (2019)
- [Exploring Tokenization Strategies and Vocabulary Sizes for Enhanced Arabic Language Models](https://mlsanity.com/paper/2403.11130/) (2024)

## Built on by (most cited first, 6 of 6)

- [Stop Taking Tokenizers for Granted: They Are Core Design Decisions in Large Language Models](https://mlsanity.com/paper/2601.13260/) (2026)
- [Trillion 7B Technical Report](https://mlsanity.com/paper/2504.15431/) (2025)
- [TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior](https://mlsanity.com/paper/2512.20757/) (2025)
- [Morphemes Without Borders: Evaluating Root-Pattern Morphology in Arabic Tokenizers and LLMs](https://mlsanity.com/paper/2603.15773/) (2026)
- [Adapting Multilingual Embedding Models to Turkish via Cross-Lingual Tokenizer Surgery and Offline Distillation](https://mlsanity.com/paper/2605.29992/) (2026)
- [TREX: Tokenizer Regression for Optimal Data Mixture](https://mlsanity.com/paper/2601.13588/) (2026)

## Abstract (arXiv)

The necessity of language-specific tokenizers intuitively appears crucial for effective natural language processing, yet empirical analyses on their significance and underlying reasons are lacking. This study explores how language-specific tokenizers influence the behavior of Large Language Models predominantly trained with English text data, through the case study of Korean. The research unfolds in two main stages: (1) the development of a Korean-specific extended tokenizer and (2) experiments to compare models with the basic tokenizer and the extended tokenizer through various Next Token Prediction tasks. Our in-depth analysis reveals that the extended tokenizer decreases confidence in incorrect predictions during generation and reduces cross-entropy in complex tasks, indicating a tendency to produce less nonsensical outputs. Consequently, the extended tokenizer provides stability during generation, potentially leading to higher performance in downstream tasks.