An empirical study showing that smaller monolingual language models are more vulnerable to adversarial attacks than larger multilingual models across 70 languages, though multilinguality alone does not guarantee security.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Weaponization: NLP Security for Medium and Lower-Resourced Languages in Their Own Right
An empirical study showing that smaller monolingual language models are more vulnerable to adversarial attacks than larger multilingual models across 70 languages, though multilinguality alone does not guarantee security.