# StochasTok: Improving Fine-Grained Subword Understanding in LLMs

arXiv: https://arxiv.org/abs/2506.01687 · HTML: https://mlsanity.com/paper/2506.01687/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 50 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 30 of 34)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale](https://mlsanity.com/paper/2406.17557/) (2024)
- [Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates](https://mlsanity.com/paper/1804.10959/) (2018)
- [Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets](https://mlsanity.com/paper/2201.02177/) (2022)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://mlsanity.com/paper/2105.13626/) (2021)
- [CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation](https://mlsanity.com/paper/2103.06874/) (2021)
- [BPE-Dropout: Simple and Effective Subword Regularization](https://mlsanity.com/paper/1910.13267/) (2019)
- [MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers](https://mlsanity.com/paper/2305.07185/) (2023)
- [Byte Latent Transformer: Patches Scale Better Than Tokens](https://mlsanity.com/paper/2412.09871/) (2024)
- [Character-Level Language Modeling with Deeper Self-Attention](https://mlsanity.com/paper/1808.04444/) (2018)
- [Teaching Arithmetic to Small Transformers](https://mlsanity.com/paper/2307.03381/) (2023)
- [Efficient Transformers with Dynamic Token Pooling](https://mlsanity.com/paper/2211.09761/) (2022)
- [SuperBPE: Space Travel for Language Models](https://mlsanity.com/paper/2503.13423/) (2025)
- [Why Do Large Language Models (LLMs) Struggle to Count Letters?](https://mlsanity.com/paper/2412.18626/) (2024)
- [What do tokens know about their characters and how do they know it?](https://mlsanity.com/paper/2206.02608/) (2022)
- [Counting Ability of Large Language Models and Impact of Tokenization](https://mlsanity.com/paper/2410.19730/) (2024)
- [CUTE: Measuring LLMs' Understanding of Their Tokens](https://mlsanity.com/paper/2409.15452/) (2024)
- [Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens](https://mlsanity.com/paper/2108.11193/) (2021)

## Built on by (most cited first, 7 of 7)

- [Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations](https://mlsanity.com/paper/2506.19004/) (2025)
- [LiteToken: Removing Intermediate Merge Residues From BPE Tokenizers](https://mlsanity.com/paper/2602.04706/) (2026)
- [Word Recovery in Large Language Models Enables Character-Level Tokenization Robustness](https://mlsanity.com/paper/2603.10771/) (2026)
- [Stochasticity in Tokenisation Improves Robustness](https://mlsanity.com/paper/2604.16037/) (2026)
- [SubTokenTest: A Practical Benchmark for Real-World Sub-token Understanding](https://mlsanity.com/paper/2601.09089/) (2026)
- [TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models](https://mlsanity.com/paper/2610.00899/) (2026)
- [What Is a Repeated Token Worth? The Scaling Geometry of Multi-Epoch Pretraining](https://mlsanity.com/paper/2610.05591/) (2026)

## Abstract (arXiv)

Subword-level understanding is integral to numerous tasks, including understanding multi-digit numbers, spelling mistakes, abbreviations, rhyming, and wordplay. Despite this, current large language models (LLMs) still struggle disproportionally with simple subword-level tasks like 'How many r's in strawberry?'. A key factor behind these failures is tokenization, which obscures the fine-grained structure of words. Current alternatives, such as character-level and dropout tokenization methods, significantly increase computational costs and provide inconsistent improvements. In this paper we revisit tokenization and introduce StochasTok, a simple, efficient stochastic tokenization scheme that randomly splits tokens during training, allowing LLMs to 'see' their internal structure. Our experiments show that pretraining with StochasTok substantially improves LLMs' downstream performance across multiple subword-level language games, including character counting, substring identification, and math tasks. Furthermore, StochasTok's simplicity allows seamless integration at any stage of the training pipeline; and we demonstrate that post-training with StochasTok can instill improved subword understanding into existing pretrained models, thus avoiding costly pretraining from scratch. These dramatic improvements achieved with a minimal change suggest StochasTok holds exciting potential when applied to larger, more capable models. Code open-sourced at: github.com/anyasims/stochastok.