Challenge: Existing research suggests that multilingual large language models can achieve impressive cross-lingual understanding despite largely monolingual pretraining.
Approach: They compare a monolingual-only corpus with a standard web corpus that removes all multilingual documents and then retrain the models from scratch under controlled conditions.
Outcome: The results show that removing bilingual data causes translation performance to drop 56% in BLEU, whereas code-switching contributes minimally.

Similar Papers

Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) exhibit remarkable multilingual capabilities despite the extreme language imbalance in the pre-training data.
Approach: They investigate the existence of code-switching in the pre-training corpus and categorize it into four types within two quadrants.
Outcome: The proposed approach improves performance across benchmarks and representation space.
Language Contamination Helps Explains the Cross-lingual Capabilities of English Pretrained Models (2022.emnlp-main)

Copied to clipboard

Challenge: a large number of pretraining corpora are not publicly available, and it is unclear how much foreign language data exists in monolingual models.
Approach: They propose to use English pretraining corpora to analyze their language composition . they find that even when less than 1% of data is not English, it facilitates cross-lingual transfer .
Outcome: The proposed model is not truly monolingual when pretrained at scale, the authors show . they show that even when less than 1% of data is not English, it facilitates cross-lingual transfer .
Multilingual Language Model Pretraining using Machine-translated Data (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for collecting and filtering multilingual web data lead to most languages lagging behind English performance due to the Internet's English-centric nature.
Approach: They propose to translate a high-quality English web corpus into nine languages and pretrain a 1.3B-parameter model on it.
Outcome: The proposed model matches or outperforms multilingual LLMs of similar size across Non-English understanding and reasoning tasks despite being trained on an order of magnitude less data.
Can Machine Translation Bridge Multilingual Pretraining and Cross-lingual Transfer Learning? (2024.lrec-main)

Copied to clipboard

Challenge: Existing models that pretrain for cross-lingual tasks do not improve cross-linguistic learning.
Approach: They propose to employ machine translation as a continued training objective to enhance language representation learning by bridging multilingual pretraining and cross-lingual applications.
Outcome: The proposed model performance is compared with existing models and their latent representations.
Emerging Cross-lingual Structure in Pretrained Language Models (2020.acl-main)

Copied to clipboard

Challenge: Recent work has shown that multilingual pretraining works, but is unable to measure these effects.
Approach: They propose to use multilingual masked language modeling to train a model on concatenated text from multiple languages to find universal latent symmetries in embedding spaces.
Outcome: The proposed models can be trained on concatenated text from multiple languages without shared vocabulary or domain similarity.
Analyzing the Mono- and Cross-Lingual Pretraining Dynamics of Multilingual Language Models (2022.emnlp-main)

Copied to clipboard

Challenge: Existing studies on multilingual models have focused on their cross-lingual transfer behavior . a recent study examined multilingual model learning from the multilingual pretraining signal .
Approach: They analyze checkpoints during multilingual pretraining to identify when models acquire in-language and cross-lingual abilities.
Outcome: The proposed model achieves high in-language performance early on, with lower-level linguistic skills acquired before more complex ones.
Data-Centric Continual Pre-training for 500+ Languages: A New Bilingual Translation Corpus and Multilingual Models (2026.findings-acl)

Copied to clipboard

Challenge: Large language models pre-trained on massive data have promoted multilingual natural language processing (NLP).
Approach: They construct a bilingual translation corpus with 2,500 language pairs and develop a suite of four models with parallel data.
Outcome: The proposed model suites are evaluated across 7 tasks and 12 benchmarks.
Assessing the Role of Data Quality in Training Bilingual Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: a recent study shows that adding more languages can degrade performance for some languages while improving others.
Approach: They propose a data filtering strategy to select high-quality bilingual training data with only high quality English data.
Outcome: The proposed approach improves bilingual model performance by 2–4% and reduces bilingual models performance gaps to 1%.
nmT5 - Is parallel data still relevant for pre-training massively multilingual language models? (2021.acl-short)

Copied to clipboard

Challenge: Recent studies have shown that cross-lingual transfer learning in pre-trained multilingual models could be improved further by incorporating parallel data.
Approach: They propose to integrate parallel data into mT5 pre-training to improve results on downstream multilingual and cross-lingual tasks.
Outcome: The proposed model improves cross-lingual transfer significantly in small fine-tuning datasets and small model sizes.
Can Monolingual Pretrained Models Help Cross-Lingual Classification? (2020.aacl-main)

Copied to clipboard

Challenge: Multilingual pretrained language models have shown impressive results for cross-lingual transfer, but due to the constant model capacity, multilingual pre-training usually lags behind the monolingual competitors.
Approach: They propose to transfer the knowledge from monolingual pretrained models to multilingual ones to improve zero-shot cross-lingual classification by using machine translation systems.
Outcome: The proposed methods outperform vanilla multilingual fine-tuning on two cross-lingual classification benchmarks.

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