arXiv:2608. 03494v1 Announce Type: cross Abstract: Vocabulary extension is an efficient way to adapt pretrained large language models (LLMs) to new languages, but the initialization of newly added token embeddings can strongly affect continued pre-training (CPT) efficiency.
The paper introduces zip2zip++, a method for inference‑time token compression that reduces token counts using a dynamic Lempel‑Ziv‑Welch (LZW) codec while preserving language model quality. It identifies four problems with prior LZW‑based compression—embedding conflict, improper RoPE application, harmful digit merges, and segmentation ambiguity—and proposes solutions: separate input/output embeddings, size‑aware RoPE, and a selective‑merge LZW codec. Experiments on four models show that these changes halve the quality gap in perplexity and reasoning accuracy compared to the uncompressed baseline, achieving similar compression ratios.
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.
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.
Manacá-1B is a 1.72‑billion‑parameter, open decoder‑only language model trained from scratch for Brazilian Portuguese, released with a fully containerized, reproducible training pipeline and complete logs. The authors evaluate it against nine open baselines on four Portuguese benchmarks, reporting standard errors and paired significance tests, and find that Manacá-1B outperforms smaller models on LAMBADA‑PT while remaining competitive on commonsense completion. They also uncover a tokenizer‑related evaluation pitfall that can drastically lower accuracy and provide a simple fix, releasing all code, logs, and corrected tokenizer for full reproducibility.
arXiv:2610.31723v1 Announce Type: new Abstract: This article introduces Latin Modern BERT (LAMB), an encoder for the Latin language based on the ModernBERT architecture, pretrained in two phases on m...
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...
arXiv:2606.23566v3 Announce Type: replace Abstract: Language-specific tokenizers improve tokenization quality and the downstream performance of models on those languages. Using one with an existing p...
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 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.
arXiv:2607.15209v4 Announce Type: replace Abstract: Multilingual pre-trained language models such as XLM-R perform well for major languages but struggle with low-resource Ge'ez-script languages, larg...
The paper examines how new vocabulary tokens are added to language models for generative recommendation tasks. It shows that the common practice of initializing these tokens as the mean of existing embeddings collapses them into a degenerate subspace, hindering fine‑tuning. The authors propose Grounded Token Initialization (GTI), which places new tokens at semantically meaningful positions in the pretrained embedding space using linguistic supervision, and demonstrate that GTI outperforms mean initialization and other adaptation methods across several benchmarks.