arXiv:2606. 15144v1 Announce Type: cross Abstract: Large language models (LLMs) process text as sequences of subword tokens, which can obscure the character-level and morphological structure that underlies word formation.
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...
SuTRA (Structurally-Unified Tokenization with Root Awareness) is a morphology-aware tokenization algorithm designed to address the problem of Morphological Shattering in morphologically rich Indic languages. It preserves the indivisibility of aksharas—complex orthographic syllables—by penalizing merges that cross morphological boundaries, thereby reducing over-fragmentation of words. The authors also release a new morphological segmentation dataset for Hindi, Marathi, and Gujarati, and demonstrate that SuTRA improves morphological alignment by up to 14.7% and semantic recoverability by 34% over BPE, leading to an average machine translation gain of +8.08 chrF2.
arXiv:2609.09974v1 Announce Type: new Abstract: Grapheme-to-phoneme conversion (G2P) refers to the task of converting a sequence of graphemes to a corresponding sequence of phonemes. While Filipino G...
arXiv:2609.36131v1 Announce Type: new Abstract: Sinhala Sandhi splitting recovers the constituent words or morphemes hidden inside a phonologically merged surface form. The task is important for Sinh...
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.
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.
The paper investigates Japanese past‑tense verb inflection in neural morphological generation systems, focusing on a rare irregular subtype where stems end in /e/ and require gemination before the suffix. Despite overall high accuracy (>97%), this <1% subclass accounts for 30–43% of residual errors, amplifying its impact by 34–48 times its frequency. Ablation experiments show that removing this specific subtype yields larger accuracy gains than removing all irregular verbs, highlighting the role of low‑frequency patterns and orthographic processes in error concentration.
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.
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:2606. 15521v1 Announce Type: cross Abstract: Tokenization introduces representational redundancy: under a fixed token vocabulary, every byte string admits many valid token encodings, or segmentations, that decode to the same surface string.
arXiv:2607. 28274v1 Announce Type: cross Abstract: Modern Greek is a richly inflected language, yet the language models built for it are evaluated mainly on factual knowledge, and no benchmark is dedicated to their inflectional competence.
The study investigates why language models exhibit systematic performance gaps across English dialects, a phenomenon termed the "dialect tax." Using parallel dialect corpora that preserve meaning while altering surface form, the authors confirm that models treat Standard American English and dialectal texts as semantically equivalent, yet find representational disparities that persist through tokenization, pre‑training, post‑training, and inference. Even a character‑level tokenizer does not eliminate input/output asymmetries or accuracy gaps, and dialect pairs produce more divergent gradient updates than unrelated Standard texts, indicating that dialectal content is harder for models to learn.