arXiv:2607. 24276v1 Announce Type: cross Abstract: Large language models (LLMs) process text through subword tokenizers rather than directly reading characters or words.
Large language models (LLMs) process text through subword tokenizers rather than directly reading characters or words. Because these tokenizers are trained predominantly on English-centric corpora, they introduce a systematic and often overlooked disadvantage for many non-English languages.
The paper introduces Universal Byte-Level Encoding (UBE), a dual‑alphabet tokenizer that routes 3‑4‑byte UTF‑8 characters through UTF‑16 while keeping 1‑2‑byte characters on the UTF‑8 path. This design lowers the worst‑case token‑budget disparity for high‑premium scripts without increasing costs for efficient English spans, and it preserves standard BPE merges and exact decoding. In extensive Unicode audits and multilingual language‑model experiments, UBE matches or improves token‑count efficiency and context usability compared to traditional byte‑pair encoding.
The paper shows that HuggingFace’s ByteLevel pre‑tokenizer, which treats a word as a sequence of Unicode letters, splits abugida scripts at every vowel sign, creating a training‑free lower bound on tokenizer fertility. Across 26 languages, all 17 abugidas exhibit increased token counts (up to 9×), while Latin, Cyrillic, Hangul, and Han remain unchanged. The authors demonstrate that correcting the character class reduces Nepali token counts, improves model performance, and that this issue is widespread in popular HuggingFace models.
The paper introduces two new tokenisation algorithms—BottomUpLL and TopDownComp—to systematically explore the 2x2 design space defined by optimisation objective (compression vs. log‑likelihood) and search procedure (bottom‑up merging vs. top‑down pruning). Experiments across model sizes, vocabularies, and domains show that the search procedure, rather than the objective, consistently yields lower bits‑per‑byte, while no clear pattern emerges on the BLiMP benchmark. These findings clarify how tokeniser design choices influence language‑model performance and provide guidance for constructing tokenisers more principledly.
arXiv:2506. 15138v2 Announce Type: replace-cross Abstract: Tokenization directly affects the inference efficiency of large language models, since fragmented tokenization increases sequence length and generation cost.
The study investigates how the choice of tokenizer influences multilingual language models across 54 tokenizers and 123 models. It finds that tokenizer impact is greater for languages with less training data, and that excluding a language from tokenizer training consistently worsens its performance. While reallocating tokenizer training data to lower-resource languages can help, it does not guarantee improvement, and the best tokenizer properties vary by language, enabling predictive screening of tokenizer candidates.
arXiv:2607. 23319v1 Announce Type: cross Abstract: Standard subword tokenization algorithms such as Byte-Pair Encoding (BPE) and SentencePiece are trained predominantly on modern language corpora and produce inefficient segmentations when applied to classical Indian languages.
Large language models are increasingly deployed as general-purpose educational and technical assistance systems, but their underlying infrastructure does not treat languages equally. One underexamined source of disparity is tokenization: semantically equivalent content can require substantially different token counts across languages, affecting API cost, latency, and usable context length before a model is invoked.
arXiv:2609.39001v1 Announce Type: cross Abstract: LLM services are billed per token and context windows are measured in tokens, yet the number of tokens needed for the same content varies across lang...
The study evaluates how extractive prompt compressors affect token costs across ten languages, finding that compressors trained on English data widen the token premium gap for non‑English languages, while a multilingual compressor does not. The gap is tied to the supervision data rather than model architecture, and aggressive compression can reduce non‑English contexts to near‑zero utility. A translate‑then‑compress approach can match or outperform native compression at roughly half the token cost in several languages.
arXiv:2508. 04796v3 Announce Type: replace-cross Abstract: Tokenization is the first -- and often least scrutinized -- step of most NLP pipelines.