ModelRefs / Multilingual Model — AI Glossary
Multilingual Model — AI Glossary
A language model trained on text from multiple languages, capable of understanding and generating content across language boundaries.
Overview
Multilingual LLMs (mBERT, BLOOM, mT5, LLaMA 3, Gemini 1.5) share a single set of weights across languages, enabling cross-lingual transfer: train on English instructions, infer in Japanese. Performance correlates with training data volume per language; low-resource languages still underperform English significantly. FLORES-200 and multilingual MMLU evaluate cross-lingual quality.
Reference details
| Topic | architecture |
|---|---|
| Also known as | cross-lingual model, multilingual LLM |
| Last reviewed | 2026-06-24 |
Related terms
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Multilingual Model — AI Glossary.
Frequently asked questions
What is Multilingual Model?
A language model trained on text from multiple languages, capable of understanding and generating content across language boundaries.
Is Multilingual Model the same as cross-lingual model?
Yes — cross-lingual model, multilingual LLM are common aliases for Multilingual Model.
What concepts are related to Multilingual Model?
Closely related concepts include machine translation, byte pair encoding, sentencepiece.