Names and span boundaries
Arabic NER corpora put the clitic inside the name
Two multilingual NER models tag ومحمد as a person, clitic included, because ANERcorp does. Half of every clitic-prefixed name in a Gulf chat set is returned one letter too long, which is the boundary a corpus wants and the wrong one for a redactor.
Detectors and language
Guard models are reported in English
Prompt-injection classifiers publish their precision and recall on English sets. Measured on the same sentences in ten languages, one widely deployed model flags 80% of ordinary Arabic customer turns as an attack, and the cause is the tokenizer vocabulary.