No Language Left Behind
No Language Left Behind (NLLB-200)
200 languages, one model, published in Nature
Latest: NLLB-200 54.5B MoE (Jul 2022); published in Nature Jun 2024
A single translation model covering 200 languages (202 language–script variants) — including 150+ low-resource ones like Asturian and Luganda — released July 6, 2022 with the FLORES-200 benchmark and training data. It averaged a 44% BLEU improvement over prior state of the art and later powered Wikipedia's Content Translation tool. Peer-reviewed in Nature (2024).
Why it matters
Proved a single model could translate 200 languages, including 150+ low-resource ones, with a 44% average BLEU gain over the prior state of the art. Its FLORES-200 benchmark became the standard multilingual test set, NLLB powers Wikipedia's Content Translation tool, and the work was peer-reviewed in Nature in 2024.
Facts
- One model that can translate between Asturian and Assamese — a pair no commercial system had ever connected.
- The flagship is a 54.5B sparse mixture-of-experts; ~150 of its languages are low-resource, and it covers 55 African languages where fewer than 25 previously had wide translation support.
- Evaluated across more than 40,000 language directions.
- Techniques from the project feed the 25 billion+ translations served daily across Meta's apps, and NLLB powers Wikipedia's Content Translation tool for low-resource languages.
- Credited to 'NLLB Team' plus 38 named authors.
Try it yourself
Model on Hugging Face (distilled 600M) ↗ Run it with Transformers (docs) ↗ Read the Nature paper ↗
Lineage
Sources
arXiv ↗GitHub · fairseq ↗Meta AI blog ↗Meta AI research ↗