The paper investigates how to fairly compare language models across languages, noting that current evaluation methods vary widely and lack empirical validation. By training controlled monolingual models on parallel data and testing multilingual LLMs, the authors find that many normalized metrics suffer from biases due to tokenization, encoding, and orthographic differences. Instead, they recommend using sentence‑level negative log‑likelihood over semantically equivalent sequences for more reliable cross‑lingual comparisons.
By Xiulin Yang, Ethan Gotlieb Wilcox, Catherine Arnett
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.
By Bruno Leonardo Santos Menezes, Carlos Leonardo Souza Cardoso, Fabio Andre Machado Porto
The paper investigates how many languages should be jointly trained in a single lexical normalization model. Using a fixed-capacity character-level model across twelve languages, it finds that accuracy peaks when a language is trained with only a few others—typically one to four—and then declines sharply as more languages are added, dropping about forty percent. A control experiment keeping total training data constant shows the decline is due to competition for model capacity rather than data scarcity, and no reliable typological rule predicts the optimal number of co‑training languages.
By Saman Rahbar
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 study evaluates phonologically informed tokenization for German speech recognition using a wav2vec 2.0 backbone fine‑tuned with CTC. Three tokenizer families—pretrained multilingual characters, data‑driven BPE, and phonologically informed units from syllabification and grapheme‑to‑phoneme conversion—are compared across 40 fine‑tunes on three German test sets (in‑domain read, dialectal spontaneous, and standard spontaneous speech). Results show that phonologically informed tokenizers match BPE and character baselines in‑domain, but under domain shift their performance depends on vocabulary size rather than linguistic variation, with syllable‑aware tokenization benefiting dialectal and spontaneous speech at small vocabularies; a phoneme‑level confusion analysis indicates that the acoustic encoder dominates error patterns.
By Christopher Witzl, Tobias Bocklet, Korbinian Riedhammer
The paper evaluates four metrics—CKA, ANC, GMM dominance per token, and ILO—used to measure cross‑lingual representation sharing in multilingual language models. Across 21 models ranging from 125 M to 14 B parameters, the metrics disagree, and the authors attribute this to anisotropy, where representations cluster in a narrow embedding cone. Only ILO shows a strong, robust correlation with cross‑lingual transfer performance (Spearman’s ρ = 0.90) after controlling for model size, family, and task variation, leading the authors to recommend ILO as the primary metric alongside anisotropy diagnostics.
By Oskar Holmstr\"om, Marcel Bollmann, Marco Kuhlmann
TokEval is a tokenizer evaluation suite that introduces metrics beyond traditional fertility and compression rate, capturing linguistically and structurally meaningful properties such as UTF‑8 character boundary integrity and digit place‑value alignment for mathematics. The authors validate these metrics by pretraining language models with varied tokenizers and measuring downstream performance on bits‑per‑byte and benchmarks covering linguistic understanding, mathematical reasoning, and code generation. Their results show that information‑theoretic metrics predict language modeling performance, while structure‑sensitive metrics correlate with task accuracy, suggesting TokEval can guide tokenizer selection more principledly.
By Clara Meister
The study compares an English-only and a bilingual decoder-only model, each 310 M parameters, trained on eight diverse languages while controlling for English exposure, compute, and document overlap. After aligning on shared English vocabulary, the authors find that token embeddings appear similar, but the deeper hidden states used for prediction diverge across models. This hidden‑state mismatch grows through middle transformer layers and persists despite controls, indicating that contextual processing differs between the models.
"whyItMatters":"The findings show that embedding alignment can conceal significant internal representation differences, which is crucial for any downstream work that assumes aligned multilingual models are interchangeable."
By Anjishnu Mukherjee, Ziwei Zhu, Antonios Anastasopoulos
SyntaxBench is a diagnostic benchmark and statistical evaluation framework for character‑level reasoning in large language models, comprising five core tasks—character counting, letter containment, palindrome detection, edit distance, and longest‑string selection—and a harder substring‑extraction stress test called index_to_span. The benchmark uses paired English and random‑string inputs, zero‑, one‑, and four‑shot prompts, and evaluates models from 2B to 32B parameters across multiple reasoning modes. It reports a wide range of metrics, including exact‑match and relaxed accuracy, Cohen’s kappa, McNemar tests, bootstrap confidence intervals, Kendall’s tau, class‑conditional metrics, tokenization analysis, and multiple‑comparison‑corrected tests.
By Mohsen Larni (Department of Computer Science, University of Nevada, Las Vegas), Sobhan Ebrahimi Azar (Department of Computer Science, University of Nevada, Las Vegas), Pouyan Nahed (Department of Computer Science, University of Nevada, Las Vegas), Kazem Taghva (Department of Computer Science, University of Nevada, Las Vegas)
arXiv:2607. 22699v1 Announce Type: new Abstract: As Large Language Models (LLMs) grow more capable across diverse tasks, their (in)ability to generalize remains difficult to quantify and poorly understood beyond limited domains.
By Supantho Rakshit, Adele Goldberg, Henry Conklin
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.
By Felermino D. M. A. Ali, Millicent Ochieng, Ogbemi Ekwejunor-Etchie, Ade Famoti, Jacki O'Neill, Debjit Paul
arXiv:2608. 03803v1 Announce Type: cross Abstract: Multilingual language models are deployed across a hundred or more languages, yet most benchmarks test whether a model can perform a task _in_ a language rather than whether it commands the language itself, conflating fluency with proficiency.
By Tom\'a\v{s} Burkert, Angelika Peljak-{\L}api\'nska, David Zelen\'y