Cross-Lingual Language Model (XLM)
Definition
XLM is a model family for cross-lingual pretraining of language models.
A model family introduced by Lample and Conneau for cross-lingual pretraining with mono- and multilingual objectives.
Simply explained
The model learns from texts in various languages and is intended to leverage linguistic knowledge across language boundaries.
Why it matters in practice
The term helps to select, develop, evaluate AI systems in a well-founded manner and realistically assess their technical risks.
Example from business
A company evaluates an XLM model on German and Polish support tickets.
Limits and pitfalls
- XLM is a specific model family, not every multilingual model; language coverage and tokenization differ.
Origin & history
XLM was published in 2019 and demonstrated transfer for classification and translation.
Use in mid-sized companies
- Possible example: A company evaluates an XLM model on German and Polish support tickets.
Frequently asked questions
What does Cross-lingual Language Model (XLM) mean?
A model family introduced by Lample and Conneau for cross-lingual pretraining with mono- and multilingual objectives. What should be considered? XLM is a specific model family, not every multilingual model; language coverage and tokenization differ.
Sources
- Cross-lingual Language Model Pretraining · Lample and Conneau, Cross-lingual Language Model Pretraining
Source checked on 10.10.2026. Editorial application examples are hypothetical; no evidence of real customer results.
Editorially reviewed on: