# What Tokens are Learned when Tokenization is Optimized Jointly with Language Modeling?

arXiv: https://arxiv.org/abs/2608.17325 · HTML: https://mlsanity.com/paper/2608.17325/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Builds on (most cited first, 28 of 28)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (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)
- [Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates](https://mlsanity.com/paper/1804.10959/) (2018)
- [One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling](https://mlsanity.com/paper/1312.3005/) (2013)
- [BPE-Dropout: Simple and Effective Subword Regularization](https://mlsanity.com/paper/1910.13267/) (2019)
- [Byte Pair Encoding is Suboptimal for Language Model Pretraining](https://mlsanity.com/paper/2004.03720/) (2020)
- [Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages](https://mlsanity.com/paper/2212.05409/) (2022)
- [Tokenization Is More Than Compression](https://mlsanity.com/paper/2402.18376/) (2024)
- [Dynamic Chunking for End-to-End Hierarchical Sequence Modeling](https://mlsanity.com/paper/2507.07955/) (2025)
- [SuperBPE: Space Travel for Language Models](https://mlsanity.com/paper/2503.13423/) (2025)
- [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)
- [MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling](https://mlsanity.com/paper/2403.10691/) (2024)
- [Greed is All You Need: An Evaluation of Tokenizer Inference Methods](https://mlsanity.com/paper/2403.01289/) (2024)
- [Boundless Byte Pair Encoding: Breaking the Pre-tokenization Barrier](https://mlsanity.com/paper/2504.00178/) (2025)
- [BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training](https://mlsanity.com/paper/2409.04599/) (2024)
- [A Bit of a Problem: Measurement Disparities in Dataset Sizes Across Languages](https://mlsanity.com/paper/2403.00686/) (2024)
- [Evaluating Morphological Alignment of Tokenizers in 70 Languages](https://mlsanity.com/paper/2507.06378/) (2025)
- [Confounding Factors in Relating Model Performance to Morphology](https://mlsanity.com/paper/2511.01380/) (2025)
- [Lexically Grounded Subword Segmentation](https://mlsanity.com/paper/2406.13560/) (2024)
- [On the Importance of Subword Information for Morphological Tasks in Truly Low-Resource Languages](https://mlsanity.com/paper/1909.12375/) (2019)
- [Rethinking Tokenization for Rich Morphology: The Dominance of Unigram over BPE and Morphological Alignment](https://mlsanity.com/paper/2508.08424/) (2025)
- [Subword Segmental Language Modelling for Nguni Languages](https://mlsanity.com/paper/2210.06525/) (2022)
- [Entropy-Driven Pre-Tokenization for Byte-Pair Encoding](https://mlsanity.com/paper/2506.15889/) (2025)
- [Stop Taking Tokenizers for Granted: They Are Core Design Decisions in Large Language Models](https://mlsanity.com/paper/2601.13260/) (2026)
- [The Learning Dynamics of Subword Segmentation for Morphologically Diverse Languages](https://mlsanity.com/paper/2511.09197/) (2025)

## Abstract (arXiv)

Tokenization is a fundamental component of language modeling pipelines. Despite its importance, it is often fixed, even though it significantly impacts model performance across languages. In this work, we analyze what tokens are learned when tokenization is jointly optimized with language modeling. We compare tokenizer-free approaches such as SSLMs and H-Nets with fixed tokenizers across 18 typologically and script-diverse languages. Our results show that joint optimization fundamentally alters token structure. SSLMs recover morphologically aligned and contextually efficient tokens, whereas H-Nets prioritize byte-level efficiency, producing longer tokens with very low overlap with standard subword vocabularies. We further show that tokenization behavior varies across language typologies. Agglutinative languages exhibit more dynamic segmentation patterns while learning. Through downstream evaluation, with pretrained-then-finetuned BERT models, we find that SSLM-based pretokenization consistently reduces language modeling perplexity and achieves competitive downstream performance despite distinct vocabularies. Overall, tokenizer-free approaches optimize for contextual and computational efficiency rather than strict morphological structure, resulting in fundamentally different yet effective vocabularies for downstream NLP.