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

• URL: http://arxiv.org/abs/2608.17325v1
• Date: Tue, 18 Aug 2026 03:34:56 GMT
• Title: What Tokens are Learned when Tokenization is Optimized Jointly with Language Modeling?
• Abstract summary: Tokenization is a fundamental component of language modeling pipelines.<n>In this work, we analyze what tokens are learned when tokenization is jointly optimized with language modeling.<n>We compare tokenizer-free approaches such as SSLMs and H-Nets with fixed tokenizers across 18 typologically and script-diverse languages.
• Score: 1.3177681589844814
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• LiteToken: Removing Intermediate Merge Residues From BPE Tokenizers [76.59130257385826]
  Intermediate merge residues in BPE vocabularies are frequent during merge learning so that retained in the final vocabulary, but are mostly further merged and rarely emitted when tokenizing the corpus during tokenizer usage.<n>We present a systematic empirical characterization of this phenomenon across commonly used tokenizers and introduce LiteToken, a simple method for removing residue tokens.<n>Experiments show that LiteToken reduces token fragmentation, reduces parameters, and improves robustness to noisy or misspelled inputs, while preserving overall performance.
  arXiv  Detail & Related papers  (2026-02-04T16:19:05Z)
• Lossless Vocabulary Reduction for Auto-Regressive Language Models [21.015330660860865]
  Tokenization -- the process of decomposing a given text into a sequence of subwords called tokens -- is one of the key components in the development of language models.<n>We establish a theoretical framework of lossless vocabulary reduction, which efficiently converts a given auto-regressive language model into the one with an arbitrarily small vocabulary.<n>As an application, we demonstrate that language models with different tokenization can cooperate with each other efficiently through their maximal common vocabulary.
  arXiv  Detail & Related papers  (2025-10-09T11:38:48Z)
• Tokens with Meaning: A Hybrid Tokenization Approach for NLP [0.2826977330147589]
  Tokenization plays a pivotal role in natural language processing (NLP)<n>We introduce a hybrid tokenization framework that combines rule-based morphological analysis with statistical subword segmentation.<n>The method uses phono normalization, root-affix, and a novel algorithm that balances morpheme preservation with vocabulary efficiency.
  arXiv  Detail & Related papers  (2025-08-19T22:17:42Z)
• Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations [83.93566096400723]
  We find that instruction-tuned models retain up to 93.4% of their original performance when given a randomly sampled tokenization.<n>Character-level segmentation improves string manipulation and code understanding tasks by up to +14%.<n>Right-aligned digit grouping enhances large-number arithmetic by +33%.
  arXiv  Detail & Related papers  (2025-06-23T18:02:26Z)
• Sampling from Your Language Model One Byte at a Time [82.71473348639489]
  Tokenization can introduce distortion into the model's generations, known as the Prompt Boundary Problem (PBP)<n>We present an inference-time method to convert any autore LM with a BPE tokenizer into a character-level or byte-level LM.<n>Our method efficiently solves the PBP and is also able to unify the vocabularies of language models with different tokenizers.
  arXiv  Detail & Related papers  (2025-06-17T02:37:04Z)
• Tokenization is Sensitive to Language Variation [14.568179478275255]
  Tokenizers split texts into smaller units and might behave differently for less common linguistic forms.<n>This might affect downstream LLM performance differently on two types of tasks.<n>We find that the best tokenizer varies on the two task types and that the pre-tokenizer has the biggest overall impact on performance.
  arXiv  Detail & Related papers  (2025-02-21T09:58:54Z)
• MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization [81.83460411131931]
  In multilingual settings, non-Latin scripts and low-resource languages are usually disadvantaged in terms of language models' utility, efficiency, and cost. We propose multilingual adaptive gradient-based tokenization to reduce over-segmentation via adaptive gradient-based subword tokenization.
  arXiv  Detail & Related papers  (2024-07-11T18:59:21Z)
• MANTa: Efficient Gradient-Based Tokenization for Robust End-to-End Language Modeling [0.0]
  We propose MANTa, a Module for Adaptive Neural TokenizAtion. ManTa is a differentiable tokenizer trained end-to-end with the language model. We show that MANTa performs comparably to other models on the general-domain GLUE benchmark.
  arXiv  Detail & Related papers  (2022-12-14T15:33:44Z)
• A Vocabulary-Free Multilingual Neural Tokenizer for End-to-End Task Learning [8.052271364177988]
  Subword tokenization is a commonly used input pre-processing step in most recent NLP models. We propose a vocabulary-free neural tokenizer by distilling segmentation information from subword tokenization. Our tokenizer consistently improves performance on multilingual (NLI) and code-switching (sentiment analysis) tasks.
  arXiv  Detail & Related papers  (2022-04-22T16:50:49Z)
• On The Ingredients of an Effective Zero-shot Semantic Parser [95.01623036661468]
  We analyze zero-shot learning by paraphrasing training examples of canonical utterances and programs from a grammar. We propose bridging these gaps using improved grammars, stronger paraphrasers, and efficient learning methods. Our model achieves strong performance on two semantic parsing benchmarks (Scholar, Geo) with zero labeled data.
  arXiv  Detail & Related papers  (2021-10-15T21:41:16Z)
• Charformer: Fast Character Transformers via Gradient-based Subword Tokenization [50.16128796194463]
  We propose a new model inductive bias that learns a subword tokenization end-to-end as part of the model. We introduce a soft gradient-based subword tokenization module (GBST) that automatically learns latent subword representations from characters. We additionally introduce Charformer, a deep Transformer model that integrates GBST and operates on the byte level.
  arXiv  Detail & Related papers  (2021-06-23T22:24:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.