# You Can Have Your Data and Balance It Too: Towards Balanced and Efficient Multilingual Models

arXiv: https://arxiv.org/abs/2210.07135 · HTML: https://mlsanity.com/paper/2210.07135/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge distillation for LLMs, one of 12 directions in Knowledge distillation.
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 13 Oct 2022.

## Placed in

- Knowledge distillation / [Knowledge distillation for LLMs](https://mlsanity.com/distill/knowledge-distillation-for-llms/)

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization](https://mlsanity.com/paper/2003.11080/) (2020)
- [On the Cross-lingual Transferability of Monolingual Representations](https://mlsanity.com/paper/1910.11856/) (2019)
- [MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer](https://mlsanity.com/paper/2005.00052/) (2020)
- [How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models](https://mlsanity.com/paper/2012.15613/) (2020)
- [Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection](https://mlsanity.com/paper/2004.10643/) (2020)
- [Are All Languages Created Equal in Multilingual BERT?](https://mlsanity.com/paper/2005.09093/) (2020)
- [Cross-Lingual Ability of Multilingual BERT: An Empirical Study](https://mlsanity.com/paper/1912.07840/) (2019)
- [When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language Models](https://mlsanity.com/paper/2010.12858/) (2020)
- [Balancing Training for Multilingual Neural Machine Translation](https://mlsanity.com/paper/2004.06748/) (2020)
- [Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages](https://mlsanity.com/paper/2205.12654/) (2022)
- [Small and Practical BERT Models for Sequence Labeling](https://mlsanity.com/paper/1909.00100/) (2019)
- [A Balanced Data Approach for Evaluating Cross-Lingual Transfer: Mapping the Linguistic Blood Bank](https://mlsanity.com/paper/2205.04086/) (2022)
- [Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation](https://mlsanity.com/paper/2004.10171/) (2020)
- [Parsing with Multilingual BERT, a Small Corpus, and a Small Treebank](https://mlsanity.com/paper/2009.14124/) (2020)

## Built on by (most cited first, 6 of 6)

- [Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages](https://mlsanity.com/paper/2305.17179/) (2023)
- [MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization](https://mlsanity.com/paper/2407.08818/) (2024)
- [A Representative Study on Human Detection of Artificially Generated Media Across Countries](https://mlsanity.com/paper/2312.05976/) (2023)
- [PuoBERTa: Training and evaluation of a curated language model for Setswana](https://mlsanity.com/paper/2310.09141/) (2023)
- [Optimal word order for non-causal text generation with Large Language Models: the Spanish case](https://mlsanity.com/paper/2502.14451/) (2025)
- [An In-Vitro Study on Cross-Lingual Generalization in Language Models](https://mlsanity.com/paper/2605.26683/) (2026)

## Abstract (arXiv)

Multilingual models have been widely used for cross-lingual transfer to low-resource languages. However, the performance on these languages is hindered by their underrepresentation in the pretraining data. To alleviate this problem, we propose a novel multilingual training technique based on teacher-student knowledge distillation. In this setting, we utilize monolingual teacher models optimized for their language. We use those teachers along with balanced (sub-sampled) data to distill the teachers' knowledge into a single multilingual student. Our method outperforms standard training methods in low-resource languages and retrains performance on high-resource languages while using the same amount of data. If applied widely, our approach can increase the representation of low-resource languages in NLP systems.