arXiv:2511. 20849v2 Announce Type: replace-cross Abstract: We introduce a new tokenizer for language models that minimizes the average tokens per character, thereby reducing the number of tokens needed to represent text during training and to generate text during inference.
arXiv:2610.22529v1 Announce Type: new Abstract: Autoregressive foundation language models predominantly target high-resource Indo-European languages, imposing computational and morphological penaltie...
arXiv:2609.06898v1 Announce Type: cross Abstract: Byte Pair Encoding (BPE) constructs vocabularies through greedy pair merging, but the resulting merge order does not necessarily allocate a fixed mod...
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.
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.
arXiv:2609.13154v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have made prompts increasingly large and complex. Techniques such as chain-of-thought reasoning (Wei et...
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.
The paper demonstrates that a byte‑level BPE tokenizer can be sliced to create multiple vocabulary sizes from a single trained model, preserving exact logits while reducing deployed weights by 66%. Experiments on 30 models show that while sliced models match the full model numerically, they underperform fixed‑cap specialists by a few percentage points in bits‑per‑byte. Multi‑cap training improves robustness to typographical noise, suggesting benefits from training across multiple granularities rather than from control tokens alone.
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:2511. 04919v3 Announce Type: replace Abstract: Processing long documents with large language models (LLMs) is expensive: a single query over a 100K-token document can cost from tens of cents to over a dollar in API fees, depending on the model, and memory grows linearly with context length.
arXiv:2607. 15232v1 Announce Type: cross Abstract: A tokenizer fixed at the start of pre-training allocates vocabulary in proportion to the pre-training corpus, reflecting the deployment priorities at that time.
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.