arXiv Computation and Language
The paper introduces the Latent Core Tokenizer (LCT), a language‑agnostic method that first discovers reusable linguistic units using Minimum Description Length, entropy‑based boundary signals, and morphotactic constraints before building a shared vocabulary. With a 200K‑token vocabulary across 104 languages, LCT shows lower fertility and higher MorphScore than BPE, Unigram, and parity‑aware BPE, while keeping tokenization cost comparable across languages. On four multilingual downstream benchmarks, LCT outperforms the baselines by 1.48, 1.83, and 2.00 aggregate points, demonstrating that compression alone does not guarantee representation quality and underscoring the role of morphology‑driven structural discovery.
The paper introduces TokenAdapt, a model‑agnostic tokenizer transplantation method that uses a hybrid heuristic to initialize new token embeddings, and a novel pre‑tokenization learning approach for multi‑word Supertokens to improve compression. TokenAdapt combines local subword decomposition and global semantic similarity to preserve semantics while reducing retraining needs. Empirical results show that TokenAdapt outperforms existing baselines such as Transtokenizer and ReTok, achieving lower perplexity ratios and significant compression gains.
By Shaurya Sharthak, Vinayak Pahalwan, Adithya Kamath, Adarsh Shirawalmath
The paper proposes a modular tokenizer framework for multilingual large language models, allowing the creation of language‑specific subtokenizers that match monolingual compression quality. It introduces a pretraining strategy that samples these subtokenizers to limit predictions to relevant vocabularies, enabling efficient training and inference. This approach reduces memory usage and speeds up inference without compromising performance.
By Franck Signe, Hippolyte Pilchen, Fran\c{c}ois Yvon, \'Edouard Grave
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.
By Ahmetcan Yavuz, Clara Meister, Tiago Pimentel
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.
By Poornima Kumaresan, Pavithra Muruganantham, Lakshmi Rajendran, Santhosh Sivasubramani
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.
By Gyeongje Cho, Yeonkyoung So, Sangmin Lee, Jaejin Lee
Multilingual Large Language Models (LLMs) traditionally rely on a single vocabulary shared by all supported languages, which can lead to uneven compression across them. Moreover, their large embedding...
arXiv:2508. 04796v3 Announce Type: replace-cross Abstract: Tokenization is the first -- and often least scrutinized -- step of most NLP pipelines.
By Negar Foroutan, Clara Meister, Debjit Paul, Joel Niklaus, Sina Ahmadi, Antoine Bosselut, Rico Sennrich
arXiv:2609.15991v1 Announce Type: new
Abstract: Standard subword tokenizers either treat every orthographic variation of a word (such as hello, Hello, HELLO, and H\'ello) as unrelated vocabulary entr...
By Connor Makowski, Willem Guter
arXiv:2610.08794v1 Announce Type: new
Abstract: Large language models rely on subword tokenizers whose quality varies across languages, yet no standardized multi-metric framework exists for broad com...
By Ben Gubler
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.
By Clara Meister, G\"ul Sena Alt{\i}nta\c{s}, Antoine Bosselut
The paper investigates how to effectively pre‑train language models when the data budget is limited but compute is plentiful. It shows that increasing model size only improves performance up to an optimal point, after which overfitting degrades generalization, and that this optimal size varies with both the data budget and downstream tasks. To overcome the inefficiencies of standard Transformers in this regime, the authors propose recursive Transformers that reuse a shared block across depth and employ factorized embeddings, achieving better results than standard models on 10M–100M word pre‑training budgets and competitive performance with BabyLM Challenge 2025 winners.
By Serdar G\"ulbahar, Lukas Edman, Alexander Fraser
arXiv:2609. 21362v1 Announce Type: new Abstract: Conventional tokenizers represent text as characters or statistically derived subwords, overlooking the internal phonological structure of syllables and often requiring large vocabularies.
By Nghia Hieu Nguyen, Thai Bao Huynh, Binh-An Dinh-Le, Phu Gia Hoang, Dat Tien Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen