Data-Centric Continual Pre-training for 500+ Languages: A New Bilingual Translation Corpus and Multilingual Models

This paper investigates a critical design decision in the practice of massively multilingual continual pre-training -the inclusion of parallel data. Specifically, we study the impact of bilingual translation data for massively multilingual language adaptation of the Llama3 family of models to 500 languages. To this end, we construct a bilingual translation corpus named MaLA, containing data from more than 2,500 language pairs. Subsequently, we develop the EMMA-500 Llama 3 suite of four massively multilingual models -continually pre-trained from the Llama 3 family of base models extensively on diverse data mixes up to 671B tokens -and explore the effect of continual pre-training with or without bilingual translation data. Comprehensive evaluation across 7 tasks and 12 benchmarks demonstrates that bilingual data tends to enhance language transfer and performance, particularly for lowresource languages. We open-source the MaLA corpus, EMMA-500 Llama 3 suite artefacts, code, and model generations.