One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers

• URL: http://arxiv.org/abs/2506.10766v1
• Date: Thu, 12 Jun 2025 14:47:13 GMT
• Title: One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers
• Authors: Diana Abagyan, Alejandro R. Salamanca, Andres Felipe Cruz-Salinas, Kris Cao, Hangyu Lin, Acyr Locatelli, Marzieh Fadaee, Ahmet Üstün, Sara Hooker,
• Abstract summary: We study what relatively cheap interventions early on in training improve "language plasticity"<n>We propose using a universal tokenizer that is trained for more languages than the primary pretraining languages.
• Score: 43.91164842493269
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Pretraining massively multilingual Large Language Models (LLMs) for many languages at once is challenging due to limited model capacity, scarce high-quality data, and compute constraints. Moreover, the lack of language coverage of the tokenizer makes it harder to address the gap for new languages purely at the post-training stage. In this work, we study what relatively cheap interventions early on in training improve "language plasticity", or adaptation capabilities of the model post-training to new languages. We focus on tokenizer design and propose using a universal tokenizer that is trained for more languages than the primary pretraining languages to enable efficient adaptation in expanding language coverage after pretraining. Our systematic experiments across diverse groups of languages and different training strategies show that a universal tokenizer enables significantly higher language adaptation, with up to 20.2% increase in win rates compared to tokenizers specific to pretraining languages. Furthermore, a universal tokenizer also leads to better plasticity towards languages that are completely unseen in the tokenizer and pretraining, by up to 5% win rate gain. We achieve this adaptation to an expanded set of languages with minimal compromise in performance on the majority of languages included in pretraining.

Related papers

• CoCo-CoLa: Evaluating and Improving Language Adherence in Multilingual LLMs [1.2057938662974816]
  Large Language Models (LLMs) develop cross-lingual abilities despite being trained on limited parallel data.<n>We introduce CoCo-CoLa, a novel metric to evaluate language adherence in multilingual LLMs.
  arXiv  Detail & Related papers  (2025-02-18T03:03:53Z)
• LlamaTurk: Adapting Open-Source Generative Large Language Models for Low-Resource Language [2.9914612342004503]
  This study explores an alternative solution by adapting large language models, primarily trained on English, to low-resource languages. We assess various strategies, including continual training, instruction fine-tuning, task-specific fine-tuning, and vocabulary extension. The results show that continual training improves language comprehension, as reflected in perplexity scores, and task-specific tuning generally enhances performance of downstream tasks.
  arXiv  Detail & Related papers  (2024-05-13T13:41:59Z)
• No Train but Gain: Language Arithmetic for training-free Language Adapters enhancement [59.37775534633868]
  We introduce a novel method called language arithmetic, which enables training-free post-processing. The effectiveness of the proposed solution is demonstrated on three downstream tasks in a MAD-X-based set of cross-lingual schemes.
  arXiv  Detail & Related papers  (2024-04-24T08:52:40Z)
• The Role of Language Imbalance in Cross-lingual Generalisation: Insights from Cloned Language Experiments [57.273662221547056]
  In this study, we investigate an unintuitive novel driver of cross-lingual generalisation: language imbalance. We observe that the existence of a predominant language during training boosts the performance of less frequent languages. As we extend our analysis to real languages, we find that infrequent languages still benefit from frequent ones, yet whether language imbalance causes cross-lingual generalisation there is not conclusive.
  arXiv  Detail & Related papers  (2024-04-11T17:58:05Z)
• Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed? [40.13166574854085]
  We investigate the minimal amount of multilinguality required to elicit cross-lingual generalisation in English-centric large language models. We find that multilingual instruction tuning with as few as two to three languages is both necessary and sufficient to elicit effective cross-lingual generalisation.
  arXiv  Detail & Related papers  (2023-12-20T00:49:52Z)
• Soft Language Clustering for Multilingual Model Pre-training [57.18058739931463]
  We propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods.
  arXiv  Detail & Related papers  (2023-06-13T08:08:08Z)
• Towards continually learning new languages [66.36852845415916]
  batch-learning of languages can be economically beneficial, but the main challenge is catastrophic forgetting. We combine the qualities of weight factorization and elastic weight consolidation in order to counter catastrophic forgetting. We achieve 26 languages without catastrophic forgetting and a reasonable performance compared to training all languages from scratch.
  arXiv  Detail & Related papers  (2022-11-21T18:24:34Z)
• Phylogeny-Inspired Adaptation of Multilingual Models to New Languages [43.62238334380897]
  We show how we can use language phylogenetic information to improve cross-lingual transfer leveraging closely related languages. We perform adapter-based training on languages from diverse language families (Germanic, Uralic, Tupian, Uto-Aztecan) and evaluate on both syntactic and semantic tasks.
  arXiv  Detail & Related papers  (2022-05-19T15:49:19Z)
• Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferability [26.553524219316188]
  Pretrained multilingual models enable zero-shot learning even for unseen languages. It is unclear how the number of pretraining languages influences a model's zero-shot learning for languages unseen during pretraining.
  arXiv  Detail & Related papers  (2022-03-21T06:52:38Z)
• Discovering Representation Sprachbund For Multilingual Pre-Training [139.05668687865688]
  We generate language representation from multilingual pre-trained models and conduct linguistic analysis. We cluster all the target languages into multiple groups and name each group as a representation sprachbund. Experiments are conducted on cross-lingual benchmarks and significant improvements are achieved compared to strong baselines.
  arXiv  Detail & Related papers  (2021-09-01T09:32:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.