# Length-MAX Tokenizer for Language Models

arXiv: https://arxiv.org/abs/2511.20849 · HTML: https://mlsanity.com/paper/2511.20849/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 25 Nov 2025.

## Builds on (most cited first, 22 of 22)

- [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)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale](https://mlsanity.com/paper/2406.17557/) (2024)
- [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://mlsanity.com/paper/2105.13626/) (2021)
- [TinyStories: How Small Can Language Models Be and Still Speak Coherent English?](https://mlsanity.com/paper/2305.07759/) (2023)
- [CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation](https://mlsanity.com/paper/2103.06874/) (2021)
- [Byte Pair Encoding is Suboptimal for Language Model Pretraining](https://mlsanity.com/paper/2004.03720/) (2020)
- [Byte Latent Transformer: Patches Scale Better Than Tokens](https://mlsanity.com/paper/2412.09871/) (2024)
- [Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies](https://mlsanity.com/paper/2407.13623/) (2024)
- [Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs](https://mlsanity.com/paper/2402.14903/) (2024)
- [Tokenizer Choice For LLM Training: Negligible or Crucial?](https://mlsanity.com/paper/2310.08754/) (2023)
- [Tokenization Is More Than Compression](https://mlsanity.com/paper/2402.18376/) (2024)
- [Shortformer: Better Language Modeling using Shorter Inputs](https://mlsanity.com/paper/2012.15832/) (2020)
- [SuperBPE: Space Travel for Language Models](https://mlsanity.com/paper/2503.13423/) (2025)
- [Impact of Tokenization on Language Models: An Analysis for Turkish](https://mlsanity.com/paper/2204.08832/) (2022)
- [Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance](https://mlsanity.com/paper/2403.06265/) (2024)
- [Tokenization and the Noiseless Channel](https://mlsanity.com/paper/2306.16842/) (2023)
- [Two Counterexamples to Tokenization and the Noiseless Channel](https://mlsanity.com/paper/2402.14614/) (2024)
- [MorphPiece : A Linguistic Tokenizer for Large Language Models](https://mlsanity.com/paper/2307.07262/) (2023)
- [Constructing a BPE Tokenization DFA](https://mlsanity.com/paper/2405.07671/) (2024)
- [BlockBPE: Parallel BPE Tokenization](https://mlsanity.com/paper/2507.11941/) (2025)

## Built on by (most cited first, 1 of 1)

- [Lifecycle-Optimal Tokenization: Vocabulary Size as a Deployment-Regime-Dependent Infrastructure Parameter](https://mlsanity.com/paper/2608.11361/) (2026)

## Abstract (arXiv)

We introduce a new tokenizer for language models that minimizes the average tokens per character, thereby reducing the number of tokens needed to represent text during training and to generate text during inference. Our method, which we refer to as the Length-MAX tokenizer, obtains its vocabulary by casting a length-weighted objective maximization as a graph partitioning problem and developing a greedy approximation algorithm. On FineWeb and diverse domains, it yields 14--18% fewer tokens than Byte Pair Encoding (BPE) across vocabulary sizes from 10K to 50K, and the reduction is 13.0% when the size is 64K. Training GPT-2 models at 124M, 355M, and 1.3B parameters from scratch with five runs each shows 18.5%, 17.2%, and 18.5% fewer steps, respectively, to reach a fixed validation loss, and 13.7%, 12.7%, and 13.7% lower inference latency, together with a 16% throughput gain at 124M, while consistently improving on downstream tasks including reducing LAMBADA perplexity by 11.7% and enhancing HellaSwag accuracy by 4.3%. Moreover, the Length-MAX tokenizer achieves 99.62% vocabulary coverage and the out-of-vocabulary rate remains low at 0.12% on test sets. These results demonstrate that optimizing for average token length, rather than frequency alone, offers an effective approach to more efficient language modeling without sacrificing -- and often improving -- downstream performance. The tokenizer is compatible with production systems and reduces embedding and KV-cache memory by 18% at inference.