Challenge: Tokenizer transfer allows training a model for low-resource languages without full retraining . a study of pre-trained tokenizers shows that they are more efficient than traditional training methods.
Approach: They evaluate tokenizer transfer on models trained on language-specific corpora, Orthogonal Mapping Pursuit and Fast Vocabulary Transfer.
Outcome: The proposed model adapts to a pre-trained model without full retraining and improves cross-lingual applicability.

Similar Papers

Modular Monolingual Adaptation using Pretrained Language Models (2026.acl-industry)

Copied to clipboard

Challenge: Existing approaches to building monolingual models for low-resource languages require a full model tuning process.
Approach: They propose a modular approach to build monolingual models for low-resource languages by finetuning the whole model on the target language.
Outcome: The proposed model improves on natural language understanding tasks on Scottish Gaelic, Irish, and Quechua with Quechuan being a very low-resource language.
Evaluating Tokenizer Adaptation Methods for Large Language Models on Low-Resource Programming Languages (2025.acl-srw)

Copied to clipboard

Challenge: Large language models (LLMs) trained on high-resource programming languages perform sub-optimally for low-resourced programming languages (LRPLs).
Approach: They evaluate the impact of tokenizer adaptation methods on improving code generation for LRPLs.
Outcome: The proposed methods outperform the original models and fine-tuned models in LRPLs, but performance declines in non-target languages like Python after tokenizer adaptation.
How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models (2021.acl-long)

Copied to clipboard

Challenge: Using pretraining data, we find that a designated monolingual tokenizer plays an equally important role in the downstream performance of the model.
Approach: They propose to compare pretrained multilingual models with their monolingual counterparts on a set of five diverse monolingual downstream tasks.
Outcome: The proposed models offer previously unmatched performance in all NLP tasks.
Tokenizer-Aware Cross-Lingual Adaptation of Decoder-Only LLMs through Embedding Relearning and Swapping (2026.eacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been primarily focused on English, leaving the multilingual ability unexplored.
Approach: They propose a technique that creates new tokenizers and tunes embeddings on fixed model weights for target language adaptation.
Outcome: The proposed method is light-weight and performant but has limitations for older models and high resource languages.
Tokenizer Choice For LLM Training: Negligible or Crucial? (2024.findings-naacl)

Copied to clipboard

Challenge: Recent success of large language models has been driven by curating the training dataset composition, scaling of model architectures and advancements in pretraining objectives, leaving tokenizer influence as a blind spot.
Approach: They conduct a comprehensive study on the influence of tokenizer choice on LLM downstream performance by training 24 mono- and multilingual LLMs at a 2.6B parameter scale.
Outcome: The proposed model can significantly impact the model's downstream performance and training costs.
One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to train multilingual large language models for many languages at once are limited due to limited model capacity, scarce high-quality data, and compute constraints.
Approach: They propose to use a universal tokenizer to improve language plasticity and adaptability to new languages by up to 20%.
Outcome: The proposed tokenizer improves language plasticity and improves plasticity towards languages that are completely unseen in the tokenizer and pretraining, by up to 5% win rate gain.
AdaptBPE: From General Purpose to Specialized Tokenizers (2026.eacl-long)

Copied to clipboard

Challenge: Subword tokenization methods impact performance and efficiency of large language models . generic tokens can incur inefficiencies when applying the model to specific domains or languages .
Approach: They propose a subword tokenization technique that selectively replaces low-utility tokens with more relevant ones based on their frequency in an adaptation corpus.
Outcome: The proposed method compresses test corpora more effectively than baselines using the same vocabulary size.
Mini-Model Adaptation: Efficiently Extending Pretrained Models to New Languages via Aligned Shallow Training (2023.findings-acl)

Copied to clipboard

Challenge: Existing approaches to pretrain Masked Language Models (MLMs) are expensive and require a full forward and backward pass over the entire model.
Approach: They propose to learn a shallow mini-model from a fraction of a large model's parameters and plug it into a larger model for rapid cross-lingual transfer.
Outcome: Experiments on XNLI, MLQA and PAWS-X show that mini-model adaptation matches the standard approach using up to 2.3x less compute on average.
UNKs Everywhere: Adapting Multilingual Language Models to New Scripts (2021.emnlp-main)

Copied to clipboard

Challenge: Massively multilingual language models offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks, but there is a profound performance gap between resource-rich and resource-poor target languages.
Approach: They propose a series of data-efficient methods that enable quick and effective adaptation of pretrained multilingual models to low-resource languages and unseen scripts.
Outcome: The proposed methods improve learning of the new dedicated embedding matrix in the target language and for low-resource languages written in unseen scripts.
MonoByte: A Pool of Monolingual Byte-level Language Models (2022.coling-1)

Copied to clipboard

Challenge: Existing studies have shown that multilingual models can achieve zero-shot cross-lingual performance on various NLP tasks, but due to the cost of pretraining, they often use public models with limited budgets.
Approach: They propose to use tokenized models to test cross-lingual ability in multilingual and monolingual corpora.
Outcome: The results show that models pretrained on multilingual and even monolingual corpora perform better than models pre-trained on SOTA models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations