Subword Tokenization

Follow this topic Ask about this topic

Subword tokenization studies how to divide text into reusable pieces that let language models handle unfamiliar words without treating every character as a separate unit. Common methods include frequency-based Byte Pair Encoding (BPE), probabilistic Unigram models, and approaches that incorporate morphology, syllables, scripts, or learned boundaries. Researchers compare tokenizers using compression and fertility measures, bits per byte, morphological alignment, multilingual benchmarks, and downstream language-model performance, since token choices affect context length, computation, and language coverage. A central tension is that compression-efficient segments do not always match linguistic structure or improve task performance, and token costs remain uneven across languages and writing systems.

Latest papers

83 papers10 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

Apr 18, 2026

How Tokenization Limits Phonological Knowledge Representation in Language Models and How to Improve Them

Tokenization is the first step in every language model (LM), yet it never takes the sounds of words into account. We investigate how tokenization influences text-only LMs' ability to represent phonological knowledge. Through a series of probing experiments, we show that subword-based tokenization systematically weakens the encoding of both local (e.g., rhyme) and global (e.g., syllabification) phonological features. To quantify this effect, we introduce the syllabification-tokenization alignment distance (STAD), a metric that measures the misalignment between a model's tokenization and the natural syllable boundaries of words, and find that higher misalignment correlates with poorer phonological representations, providing a simple diagnostic for phonology-aware tokenization. To address these limitations, we propose a lightweight IPA-based fine-tuning method that infuses phonological awareness into LMs, leading to consistent improvements across three phonology-related tasks while largely preserving math and general reasoning ability, with 1.1% and 0.9% drops on GSM8K and MMLU, respectively.

Disen Liao, Freda Shi

University of Waterloo · Vector Institute

LLM Fine-Tuning Language Modeling Subword Tokenization Tokenization in Language Models Tokenization

Apr 17, 2026

Defragmenting Language Models: An Interpretability-based Approach for Vocabulary Expansion

All languages are equal; when it comes to tokenization, some are more equal than others. Tokens are the hidden currency that dictate the cost and latency of access to contemporary LLMs. However, many languages written in non-Latin scripts observe a poor exchange rate: LLMs take several multiples of tokens to encode the same information in many languages as they do for English. Our analysis reveals that this issue, known as 'token over-fragmentation', persists in modern open-weight LLMs. The standard remedy is vocabulary expansion that adds target language items missing from the model's vocabulary. In this work, we comprehensively study and advance interpretability-based vocabulary expansion, a new research direction. We focus on two core decisions in the vocabulary expansion process: What items should we add? and How should we initialize their corresponding input and output embeddings? First, we question the conventional use of frequency-based methods to choose candidate vocabulary items to add (a decision long treated as settled), and show that interpretability-based methods offer a superior performance-token efficiency trade-off. Next, we strengthen the case for interpretability-based embedding initialization by showing large gains (~20 pts) over baseline initialization methods for several languages written in non-Latin scripts. We identify the phenomenon of "subword detokenization" where models progressively merge fragmented subword tokens into larger subwords across layers. Grounded in our analysis of this phenomenon, we propose FragMend to further push the efficiency ceiling of interpretability-based expansion. We validate the effectiveness of FragMend through comparison against strong baselines and we present extensive analysis of its design choices.

Maitrey Mehta, Nishant Subramani, Zhichao Xu +2

Kahlert School of Computing, University of Utah · Language Technologies Institute, Carnegie Mellon University

Multilingual Language Models Subword Tokenization Language Model Vocabulary Expansion Tokenization in Language Models

Apr 17, 2026

Stochasticity in Tokenisation Improves Robustness

The widespread adoption of large language models (LLMs) has increased concerns about their robustness. Vulnerabilities in perturbations of tokenisation of the input indicate that models trained with a deterministic canonical tokenisation can be brittle to adversarial attacks. Recent studies suggest that stochastic tokenisation can deliver internal representations that are less sensitive to perturbations. In this paper, we analyse how stochastic tokenisations affect robustness to adversarial attacks and random perturbations. We systematically study this over a range of learning regimes (pre-training, supervised fine-tuning, and in-context learning), data sets, and model architectures. We show that pre-training and fine-tuning with uniformly sampled stochastic tokenisations improve robustness to random and adversarial perturbations. Evaluating on uniformly sampled non-canonical tokenisations reduces the accuracy of a canonically trained Llama-1b model by 29.8%. We find that training with stochastic tokenisation preserves accuracy without increasing inference cost.

Sophie Steger, Rui Li, Sofiane Ennadir +4

Institute of Signal Processing and Speech Communication, Graz University of Technology, Graz, Austria · ELLIS Institute Finland & Aalto University, Espoo, Finland · King AI Labs, Microsoft Gaming +2

Adversarial Attacks on LLMs Neural Network Robustness Adversarial Robustness of Language Models Subword Tokenization

Apr 13, 2026

A Triadic Suffix Tokenization Scheme for Numerical Reasoning

Standard subword tokenization methods fragment numbers inconsistently, causing large language models (LLMs) to lose positional and decimal structure - a primary driver of errors in arithmetic and scientific reasoning. We introduce Triadic Suffix Tokenization (TST), a deterministic scheme that partitions digits into three-digit triads and annotates each triad with an explicit magnitude marker. Critically, the scheme defines a fixed, one-to-one mapping between suffixes and orders of magnitude for the integer part (thousands, millions, billions, etc.) and a parallel system of replicated markers for fractional depth (tenths, thousandths, millionths, etc.). Unlike approaches that rely on positional inference, this method provides a consistent gradient signal, which should ensure stable convergence. Two implementation variants are proposed: (1) a vocabulary-based approach that adds at most 10,000 fixed tokens to an existing vocabulary, covering 33 orders of magnitude (

10^{-15}

to

10^{18}

); and (2) a suffix-marker approach that uses a small set of special tokens to denote magnitude dynamically. Both variants preserve exact digits while making order-of-magnitude relationships transparent at the token level. While we focus on 3-digit groups (Triadic), the framework is inherently scalable to any group size for precise vocabulary optimization. Furthermore, it allows for linear vocabulary expansion to accommodate arbitrary precision and range. TST is architecture-agnostic and can be integrated as a drop-in preprocessing step. Experimental validation is deferred to future work.

Olga Chetverina

Lecturer at MIPT, Moscow, Russia.

Tokenization Subword Tokenization Numerical Reasoning in Language Models

Apr 12, 2026

Advancing Polish Language Modeling through Tokenizer Optimization in the Bielik v3 7B and 11B Series

The development of the Bielik v3 PL series, encompassing both the 7B and 11B parameter variants, represents a significant milestone in the field of language-specific large language model (LLM) optimization. While general-purpose models often demonstrate impressive multilingual capabilities, they frequently suffer from a fundamental architectural inefficiency: the use of universal tokenizers. These tokenizers, typically designed to cover a broad spectrum of languages, often fail to capture the morphological nuances of specific languages like Polish, leading to higher fertility ratios, increased inference costs, and restricted effective context windows. This report details the transition from the universal Mistral-based tokenization to a dedicated Polish-optimized vocabulary for the Bielik v3 models, exploring the FOCUS-based embedding initialization, the multi-stage pretraining curriculum, and the subsequent post-training alignment involving Supervised Fine-Tuning, Direct Preference Optimization, and Reinforcement Learning through Group Relative Policy Optimization with verifiable rewards.

Krzysztof Ociepa, Łukasz Flis, Remigiusz Kinas +2

SpeakLeash · Azurro · ACK Cyfronet AGH +2

Language Modeling Subword Tokenization Language Model Pretraining LLM Fine-Tuning

Apr 12, 2026

HeceTokenizer: A Syllable-Based Tokenization Approach for Turkish Retrieval

HeceTokenizer is a syllable-based tokenizer for Turkish that exploits the deterministic six-pattern phonological structure of the language to construct a closed, out-of-vocabulary (OOV)-free vocabulary of approximately 8,000 unique syllable types. A BERT-tiny encoder (1.5M parameters) is trained from scratch on a subset of Turkish Wikipedia using a masked language modeling objective and evaluated on the TQuAD retrieval benchmark using Recall@5. Combined with a fine-grained chunk-based retrieval strategy, HeceTokenizer achieves 50.3% Recall@5, surpassing the 46.92% reported by a morphology-driven baseline that uses a 200 times larger model. These results suggest that the phonological regularity of Turkish syllables provides a strong and resource-light inductive bias for retrieval tasks.

Senol Gulgonul

Electrical and Electronics Engineering, Ostim Technical University, Ankara Turkey

Tokenization Information Retrieval Subword Tokenization

Apr 6, 2026

Faster Superword Tokenization

Byte Pair Encoding (BPE) is a widely used tokenization algorithm, whose tokens cannot extend across pre-tokenization boundaries, functionally limiting it to representing at most full words. The BoundlessBPE and SuperBPE algorithms extend and improve BPE by relaxing this limitation and allowing the formation of superwords, which are combinations of pretokens that form phrases. However, previous implementations were impractical to train: for example, BoundlessBPE took 4.7 CPU days to train on 1GB of data. We show that supermerge candidates, two or more consecutive pretokens eligible to form a supermerge, can be aggregated by frequency much like regular pretokens. This avoids keeping full documents in memory, as the original implementations of BoundlessBPE and SuperBPE required, leading to a significant training speedup. We present a two-phase formulation of BoundlessBPE that separates first-phase learning of regular merges from second-phase learning of supermerges, producing identical results to the original implementation. We also show a near-equivalence between two-phase BoundlessBPE and SuperBPE, with the difference being that a manually selected hyperparameter used in SuperBPE can be automatically determined in the second phase of BoundlessBPE. These changes enable a much faster implementation, allowing training on that same 1GB of data in 603 and 593 seconds for BoundlessBPE and SuperBPE, respectively, a more than 600x increase in speed. For each of BoundlessBPE, SuperBPE, and BPE, we open-source both a reference Python implementation and a fast Rust implementation.

Craig W. Schmidt, Chris Tanner, Yuval Pinter

Kensho Technologies, Cambridge, MA 02138, USA · MIT, Cambridge, MA, USA · Institute for Applied AI Research, Ben-Gurion University of the Negev, Beer Sheva 8410501, Israel

Tokenization Subword Tokenization Byte-Pair Encoding

Mar 26, 2026

Separate Before You Compress: The WWHO Tokenization Architecture

Current Large Language Models (LLMs) mostly use BPE (Byte Pair Encoding) based tokenizers, which are very effective for simple structured Latin scripts such as English. However, standard BPE tokenizers struggle to process complex Abugida scripts due to their structural complexity. The problem is that these tokenizers break complex conjuncts, which are multi-codepoint grapheme clusters, into meaningless sub-character units. This degrades the LLM's reasoning efficiency by forcing it to learn basic orthographic structures at inference time and raises inference costs, resulting in a significant "Token Tax" for the Global South. We propose a new three-layer architecture, the WWHO (Where-What-How Often), and an algorithm named SGPE (Syllable-aware Grapheme Pair Encoding) that separates the linguistic rules of the script from the statistical compression process while enabling seamless multilingual tokenization. Using Sinhala and Devanagari (Hindi/Sanskrit) as highly complex Abugida scripts, we trained WWHO on a cleaned 30-million-sentence dataset and evaluated on a 1,499,950-sentence test set. For Sinhala, SGPE achieves a Token to Word Ratio (TWR) of 1.274 with 4.83 characters per token, representing a 61.7 percent reduction in tokens compared to OpenAI's o200k base. For Hindi, it achieves a TWR of 1.181 (27.0 percent reduction vs o200k). On the mixed-script (Sinhala, Devanagari, and English) dataset, SGPE achieves an overall TWR of 1.240, representing token reductions of 36.7 percent, 39.6 percent, and 60.2 percent relative to o200k base, Llama 4 Scout, and DeepSeek V3, respectively. This effectively extends the usable context window by up to 4.38 times for these Abugida languages while ensuring a Linguistic Zero-Breakage Guarantee, which ensures that no valid syllable is ever split across multiple tokens.

Kusal Darshana

Remeinium Research

Tokenization Subword Tokenization

Mar 25, 2026

Tokka-Bench: Evaluating Tokenizers Across 100 Natural and 20 Programming Languages

Large language models rely on subword tokenizers whose quality varies across languages, yet no standardized multi-metric framework exists for broad comparative evaluation. We introduce Tokka-Bench, an open-source framework that evaluates tokenizers on five complementary metrics -- bytes per token, unique token coverage, subword fertility, word-split rate, and vocabulary composition -- across 100 natural languages (30+ scripts) and 20 programming languages, using language-aware segmentation adapted to each writing system. Comparing seven BPE tokenizers (GPT-2, GPT-4, gpt-oss, Llama 3.1, Gemma 3, Qwen3, and Kimi K2) within individual languages, we find that vocabulary allocation strategy matters more than raw vocabulary size, and that programming-language efficiency has converged among recent tokenizers despite divergent natural-language profiles. The framework, data, and interactive dashboard are publicly available.

Ben Gubler

Tokenization in Language Models Tokenization Subword Tokenization

Mar 17, 2026

MDM-Prime-v2: Binary Encoding and Index Shuffling Enable Scaling of Diffusion Language Models

Masked diffusion models (MDM) exhibit superior generalization when learned using a Partial masking scheme (Prime). This approach converts tokens into sub-tokens and models the diffusion process at the sub-token level. We identify two limitations of the MDM-Prime framework. First, we find that the functional form of the subtokenizer significantly increases the cross-entropy loss in the objective when paired with commonly used Byte-Pair-Encoding (BPE) tokenizers. Second, we lack tools to guide the hyperparameter choice of the token granularity in the subtokenizer. To address these limitations, we analyze the optimal design of the subtokenizer that minimizes MDM-Prime training objective and develop MDM-Prime-v2, a masked diffusion language model which incorporates Binary Encoding and Index Shuffling. Our analysis characterizes how token granularity and sub-token entropy influence the training objective and downstream performance, providing principled criteria for subtokenizer design. When extending the model size to 1.1B parameters, MDM-Prime-v2 demonstrates superior average zero-shot accuracy across eight commonsense reasoning benchmarks, outperforming similar-sized baselines including GPT-Neo, OPT, Pythia, Bloom, SMDM, and TinyLLaMA.

Chen-Hao Chao, Wei-Fang Sun, Junwei Quan +2

University of Toronto, Vector Institute · NVIDIA AI Technology Center · National Taiwan University

Commonsense Reasoning Diffusion Language Models Subword Tokenization

Mar 16, 2026

Morphemes Without Borders: Evaluating Root-Pattern Morphology in Arabic Tokenizers and LLMs

This work investigates how effectively large language models (LLMs) and their tokenization schemes represent and generate Arabic root-pattern morphology, probing whether they capture genuine morphological structure or rely on surface memorization. Arabic morphological system provides a rich testbed for analyzing how LLMs handle complex, non-concatenative forms and how tokenization choices influence this process. Our study begins with an evaluation of morphological fidelity across Arabic and multilingual tokenizers against gold-standard segmentation, followed by an analysis of LLM performance in productive root-pattern generation using a newly developed test set. Our findings across seven Arabic-centric and multilingual LLMs and their respective tokenizers reveal that tokenizer morphological alignment is not necessary nor sufficient for morphological generation, which questions the role of morphological tokenization in downstream performance.

Yara Alakeel, Chatrine Qwaider, Hanan Aldarmaki +1

Saudi Data & AI Authority (SDAIA) · Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · Princess Nourah Bint Abdulrahman University (PNU)

Arabic NLP Arabic Language Models Morphology-Aware Tokenization Subword Tokenization Multilingual Language Model Evaluation

Mar 6, 2026

VerChol -- Grammar-First Tokenization for Agglutinative Languages

Tokenization is the foundational step in all large language model (LLM) pipelines, yet the dominant approach Byte Pair Encoding (BPE) and its variants is inherently script agnostic and optimized for English like morphology. For agglutinative languages a typological class encompassing the Dravidian family (Tamil, Kannada, Telugu, Malayalam), Turkic languages (Turkish, Azerbaijani, Uzbek), Uralic languages (Finnish, Hungarian, Estonian), Korean, Japanese, Swahili, Basque, and others, a single word may encode root, tense, aspect, person, number, gender agreement, case, and postpositions into one orthographic unit. Statistical tokenizers fragment these words into byte pair chunks that sever morpheme boundaries and inflate token counts.

Prabhu Raja

Bengaluru, India

Morphology-Aware Tokenization Tokenization in Language Models Tokenization Subword Tokenization

Mar 3, 2026

ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer

Modern language models still rely on fixed, pre-defined subword tokenizations. Once a tokenizer is trained, the LM can only operate at this fixed level of granularity, which often leads to brittle and counterintuitive behaviors even in otherwise strong reasoning models. We introduce ByteFlow Net, a new hierarchical architecture that removes tokenizers entirely and instead enables models to learn their own segmentation of raw byte streams into semantically meaningful units. ByteFlow Net performs compression-driven segmentation based on the coding rate of latent representations, yielding adaptive boundaries \emph{while preserving a static computation graph via Top-

K

selection}. Unlike prior self-tokenizing methods that depend on brittle heuristics with human-designed inductive biases, ByteFlow Net adapts its internal representation granularity to the input itself. Experiments demonstrate that this compression-based chunking strategy yields substantial performance gains, with ByteFlow Net outperforming both BPE-based Transformers and previous byte-level architectures. These results suggest that end-to-end, tokenizer-free modeling is not only feasible but also more effective, opening a path toward more adaptive and information-grounded language models.

Chunyuan Deng, Sanket Lokegaonkar, Colin Lockard +3

Rice University · Amazon Science

Language Modeling Byte-Level Language Model Subword Tokenization

Mar 3, 2026

GPUTOK: GPU Accelerated Byte Level BPE Tokenization

As large language models move toward million-token context windows, CPU tokenizers become a major slowdown because they process text one step at a time while powerful GPUs sit unused. We built a GPU-based byte-level BPE tokenizer that follows GPT-2's merge rules. It includes a basic BlockBPE-style kernel and a faster, optimized version that uses cuCollections static map, CUB reductions, and a pybind11 interface for Python. On WikiText103 sequences up to 131k tokens, the optimized GPU tokenizer produces the same tokens as a CPU version and, for the longest inputs, is about 1.7x faster than tiktoken and about 7.6x faster than the HuggingFace GPT-2 tokenizer. Nsight profiling shows that 70-80% of CUDA API time goes to memory allocation, so adding memory pooling should give the biggest speed boost next. Tests on generation tasks using WikiText103 prompts show that our GPU tokenizer's outputs stay within about one percentage point of tiktoken and HuggingFace GPT-2 on similarity and overlap metrics, meaning it keeps output quality while making long-context inference more practical.

Venu Gopal Kadamba, Kanishkha Jaisankar

M.S. in Data Science, New York University

Subword Tokenization LLM Inference Acceleration GPU Kernel Optimization

Feb 26, 2026

Significance-Gain Pair Encoding for LLMs: A Statistical Alternative to Frequency-Based Subword Merging

Subword tokenization is a key design choice for modern language models, including large language models (LLMs), with byte- and character-level BPE serving as a widely used baseline. Standard BPE selects merges by raw pair frequency, which favors compression but can conflate true adjacency cohesion with pairs that are frequent due to high marginal counts. This paper introduces Significance-Gain BPE, a drop-in alternative merge criterion that measures cohesion via a z-statistic under an independence null model and combines it with an explicit compression-aware gain term. Significance-Gain BPE is evaluated on WikiText-103 (raw) character slices using a small causal Transformer language model, reporting both token-dependent perplexity and the tokenizer-invariant metric bits per character (BPC). At a representative operating point, Significance-Gain BPE reduces validation and test perplexity by 13% and 12%, respectively, and improves validation and test BPC by about 0.9 to 1.0%. A vocabulary-size sweep further shows lower BPC in most closest-compression comparisons, suggesting that statistically grounded merge selection can improve predictive efficiency per unit of raw text across a range of compression regimes.

Azam Nouri

Department of Science, Technology & Mathematics, Lincoln University

Subword Tokenization Byte-Pair Encoding

Feb 25, 2026

Tokenization vs. Augmentation: A Systematic Study of Writer Variance in IMU-Based Online Handwriting Recognition

Inertial measurement unit-based online handwriting recognition enables the recognition of input signals collected across different writing surfaces but remains challenged by uneven character distributions and inter-writer variability. In this work, we systematically investigate two strategies to address these issues: subword tokenization and concatenation-based data augmentation. Our experiments on the OnHW-Words500 dataset reveal a clear dichotomy between handling inter-writer and intra-writer variance. On the writer-independent split, structural abstraction via Bigram tokenization significantly improves generalization to unseen writing styles, reducing the word error rate (WER) from 15.40% to 12.99%. In contrast, on the writer-dependent split, tokenization degrades performance due to vocabulary distribution shifts between the training and validation sets. Instead, our proposed concatenation-based data augmentation acts as a powerful regularizer, reducing the character error rate by 34.5% and the WER by 25.4%. Further analysis shows that short, low-level tokens benefit model performance and that the performance gains from concatenation-based data augmentation surpass those achieved by proportionally extended training. These findings reveal a clear variance-dependent effect: subword tokenization primarily mitigates inter-writer stylistic variability, whereas concatenation-based data augmentation effectively compensates for intra-writer distributional sparsity.

Jindong Li, Dario Zanca, Vincent Christlein +4

Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany · STABILO International GmbH, Heroldsberg, Germany · Ludwig-Maximilians-Universität München, Munich, Germany +2

Data Augmentation Online Handwriting Recognition Subword Tokenization

Feb 17, 2026

ZeroSyl: Simple Zero-Resource Syllable Tokenization for Spoken Language Modeling

Pure speech language models aim to learn language directly from raw audio without textual resources. A key challenge is that discrete tokens from self-supervised speech encoders result in excessively long sequences, motivating recent work on syllable-like units. However, methods like Sylber and SyllableLM rely on intricate multi-stage training pipelines. We propose ZeroSyl, a simple training-free method to extract syllable boundaries and embeddings directly from a frozen WavLM model. Using L2 norms of features in WavLM's intermediate layers, ZeroSyl achieves competitive syllable segmentation performance. The resulting segments are mean-pooled, discretized using K-means, and used to train a language model. ZeroSyl outperforms prior syllabic tokenizers across lexical, syntactic, and narrative benchmarks. Scaling experiments show that while finer-grained units are beneficial for lexical tasks, our discovered syllabic units exhibit better scaling behavior for syntactic modeling.

Nicol Visser, Simon Malan, Danel Slabbert +1

Electrical and Electronic Engineering, Stellenbosch University, South Africa

Audio Tokenization Speech Language Models Discrete Speech Representation Learning Subword Tokenization

Feb 15, 2026

You Can Learn Tokenization End-to-End with Reinforcement Learning

Tokenization is a hardcoded compression step which remains in the training pipeline of Large Language Models (LLMs), despite a general trend towards architectures becoming increasingly end-to-end. Prior work has shown promising results at scale in bringing this compression step inside the LLMs' architecture with heuristics to draw token boundaries, and also attempts to learn these token boundaries with straight-through estimates, which treat the problem of drawing discrete token boundaries as a continuous one. We show that these token boundaries can instead be learned using score function estimates, which have tighter theoretical guarantees due to directly optimizing the problem of drawing discrete token boundaries to minimize loss. We observe that techniques from reinforcement learning, such as time discounting, are necessary to reduce the variance of this score function sufficiently to make it practicable. We demonstrate that the resultant method outperforms prior proposed straight-through estimates, both qualitatively and quantitatively at the

100

million parameter scale.

Sam Dauncey, Roger Wattenhofer

Department of Electrical Engineering, ETH Zurich, Zurich, Switzerland.

Subword Tokenization LLM Training Tokenization in Language Models Tokenization

Dec 23, 2025

TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior

Tokenizers provide the fundamental basis through which text is represented and processed by language models (LMs). Despite the importance of tokenization, its role in LM performance and behavior is poorly understood due to the challenge of measuring the impact of tokenization in isolation. To address this need, we present TokSuite, a collection of models and a benchmark that supports research into tokenization's influence on LMs. Specifically, we release fourteen pre-trained models that use different off-the-shelf tokenizers but are otherwise identical, using the same architecture, dataset, training budget, and initialization. We also release a multilingual robustness benchmark that measures model performance under real-world perturbations in English, Chinese, Farsi, Italian, and Turkish, curated by native annotators. Together, TokSuite allows robust decoupling of the influence of a model's tokenizer, supporting a series of novel findings that elucidate the respective benefits and shortcomings of a wide range of popular tokenizers.

Gül Sena Altıntaş, Malikeh Ehghaghi, Brian Lester +4

University of Toronto · Vector Institute · Google DeepMind +4

Subword Tokenization Tokenization in Language Models

Sep 10, 2025

MoVoC: Morphology-Aware Subword Construction for Geez Script Languages Corrected version

Subword-based tokenization methods often fail to preserve morphological boundaries, a limitation especially pronounced in low-resource, morphologically complex languages such as those written in the Ge'ez script. To address this, we present Morpheme-aware Subword Vocabulary Construction (MoVoC) and train MoVoC-Tok, a tokenizer that integrates supervised morphological analysis into the subword vocabulary. This hybrid segmentation approach combines morpheme-based and Byte Pair Encoding (BPE) tokens to preserve morphological integrity while maintaining lexical meaning. To tackle resource scarcity, we release morpheme-annotated data for four Ge'ez script languages (169,806 records) and a morpheme-aware vocabulary for two of them. Scoring every comparison on words held out from the morpheme resource that constrains the MoVoC-Tok applied to that language, MoVoC-Tok has the highest MorphScore in three of four languages and the highest morpheme boundary precision in two of four, with its largest and most clearly resolved gains on Tigre, a language it was not trained on and to which it is applied cross-lingually. The machine translation results reported in the published version are withdrawn. Data, tokenizers and evaluation code are publicly available.

Hailay Kidu Teklehaymanot, Dren Fazlija, Wolfgang Nejdl

L3S Research Center, Leibniz University Hannover, Germany

Morphology-Aware Tokenization Subword Tokenization Low-Resource Language Processing

Aug 6, 2025

Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization

Tokenization is the first -- and often least scrutinized -- step of most NLP pipelines. Standard algorithms for learning tokenizers rely on frequency-based objectives, which favor languages dominant in the training data and consequently leave lower-resource languages with tokenizations that are disproportionately longer, morphologically implausible, or even riddled with

<UNK>

placeholders. This phenomenon ultimately amplifies computational and financial inequalities between users from different language backgrounds. To remedy this, we introduce Parity-aware Byte Pair Encoding (BPE), a variant of the widely-used BPE algorithm. At every merge step, Parity-aware BPE applies a fair-max rule that maximizes the compression gain of the currently worst-compressed language, trading a small amount of global compression for cross-lingual parity. We find empirically that Parity-aware BPE reduces tokenization inequality -- operationalized by the Gini coefficient of per-language token costs -- by up to 89% relative to Classical BPE. This comes with negligible impact on global compression rate and no evidence of systematic degradation in downstream LM performance.

Negar Foroutan, Clara Meister, Debjit Paul +4

EPFL · University of Zurich

Low-Resource Language Processing Subword Tokenization Byte-Pair Encoding Tokenization

Jun 18, 2025

Less Is More: Reducing Token Counts Without Compromising Performance

Tokenization directly affects the inference efficiency of large language models, since fragmented tokenization increases sequence length and generation cost. Although longer, multi-word tokens can reduce fertility, naively adding them often degrades language model performance. We propose Thunder-Tok, a subword tokenizer that reduces fertility while preserving downstream performance. Thunder-Tok first constructs a large seed vocabulary from corpus substrings and filters structurally incomplete candidates, including invalid Unicode byte fragments and word-boundary violations. It then prunes the seed vocabulary using a likelihood-based token score derived from a uniform Jensen lower bound of the training-data probability. Experiments show that Thunder-Tok reduces fertility by approximately 25% in English and 9% in Korean compared with the standard BPE tokenizer while maintaining competitive performance.

Gyeongje Cho, Yeonkyoung So, Sangmin Lee +1

Graduate School of Data Science, Seoul National University · Department of Computer Science, Seoul National University

LLM Inference Acceleration Token Efficiency Subword Tokenization Tokenization in Language Models Tokenization

Dec 14, 2024

Tokens, the oft-overlooked appetizer: Large language models, the distributional hypothesis, and meaning

Tokenization is a necessary component within the current architecture of many language mod-els, including the transformer-based large language models (LLMs) of Generative AI, yet its impact on the model's cognition is often overlooked. We argue that LLMs demonstrate that the Distributional Hypothesis (DH) is sufficient for reasonably human-like language performance (particularly with respect to inferential lexical competence), and that the emergence of human-meaningful linguistic units among tokens and current structural constraints motivate changes to existing, linguistically-agnostic tokenization techniques, particularly with respect to their roles as (1) vehicles for conveying salient distributional patterns from human language to the model and as (2) semantic primitives. We explore tokenizations from a BPE tokenizer; extant model vocabularies obtained from Hugging Face and tiktoken; and the information in exemplar token vectors as they move through the layers of a RoBERTa (large) model. Besides creating suboptimal semantic building blocks and obscuring the model's access to the necessary distributional patterns, we describe how tokens and pretraining can act as a backdoor for bias and other unwanted content, which current alignment practices may not remediate. Additionally, we relay evidence that the tokenization algorithm's objective function impacts the LLM's cognition, despite being arguably meaningfully insulated from the main system intelligence. Finally, we discuss implications for architectural choices, meaning construction, the primacy of language for thought, and LLM cognition. [First uploaded to arXiv in December, 2024.]

Julia Witte Zimmerman, Denis Hudon, Kathryn Cramer +9

Computational Story Lab, Vermont Complex Systems Institute, University of Vermont, Burlington, VT 05405, USA · Vermont Complex Systems Institute, University of Vermont, Burlington, VT 05405, USA · Department of Computer Science, St. Michael’s College, Colchester, VT 05439, USA +3

LLM Interpretability Distributional Semantics Subword Tokenization Tokenization in Language Models Tokenization