When Tokenizers Fail: Byte-Level Chunking for Zero-Shot Transfer to Low-Resource Languages

[2608.27658] When Tokenizers Fail: Byte-Level Chunking for Zero-Shot Transfer to Low-Resource Languages Skip to main content Search Submit Donate Log in Computer Science > Computation and Language arXiv:2608.27658 (cs) [Submitted on 27 Aug 2026] Title: When Tokenizers Fail: Byte-Level Chunking for Zero-Shot Transfer to Low-Resource Languages Authors: Sanjeev Kumar , Atsuki Yamaguchi , Nikolaos Aletras View PDF HTML (experimental) Abstract: Subword tokenization hinders low-resource language processing by imposing frequency patterns from dominant languages onto script-sharing variants. Byte-level models bypass this issue by processing raw UTF-8 characters, yet they create a granularity mismatch for word-level tasks in non-Latin scripts. Hierarchical byte-level architectures address this mismatch by grouping bytes into word-aligned chunks. However, these architectures require massive training data and suffer from representational misalignment when paired with frozen subword-based language models. In this paper, we propose an adapted hierarchical network framework that bridges this modality gap without extensive training. Our method initializes byte embeddings directly from the subword representations of a frozen base model. We apply a chunk alignment loss to project dynamically grouped byte chunks toward precomputed subword targets, and interleave lightweight part-of-speech (POS) supervision to guide boundary detection. Experiments across six languages demonstrate that our tokenizer-free approach improves performance for word-level morphological tasks, yielding up to a 13.3% improvement on POS tagging. Comments: Accepted to EMNLP 2026 Subjects: Computation and Language (cs.CL) Cite as: arXiv:2608.27658 [cs.CL] (or arXiv:2608.27658v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2608.27658 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Sanjeev Kumar [ view email ] [v1] Thu, 27 Aug 2026 19:45:54 UTC (1,637 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CL < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from (opens in new tab) (opens in new tab) (opens in new tab)

Related documents

• When Tokenizers Fail: Byte-Level Chunking for Zero-Shot Transfer to Low-Resource Languages#779582
• Toppling the Hierarchy in Byte-level Language Modeling#819909
• One Token Is Enough: Fingerprinting and Verifying Large Language Models from Single-Token Output Distributions#363194
• Motif-Vocab: StatisticallyCalibrated Transcription-Factor-Identity Tokenization forGenomic Language Models#1064989
• HuggingFaceFW/finetranslations#786667