3 papers
cs.CL2026
Where Are Language-Specific Features Represented in Multilingual LLMs? Everywhere
Mikaela Martins, Jonathan Dunn
Previous work has argued that multilingual LLMs encode language-specific features most strongly in their initial and final layers, implying that intermediate layers support languag…
cs.CL2026
Some Dialects Are More Equal Than Others: Non-Prestigious Arabic Dialectal Bias in LLMs
Mai Mohamed Eida, Ryan Dolan, Paul de Nijs +1
Previous work on Egyptian Arabic in NLP has focused largely on the prestigious Cairene Egyptian Arabic (CEA) dialect, resulting in a lack of representation for the less prestigious…
cs.CL2025
LLMs Learn Constructions That Humans Do Not Know
Jonathan Dunn, Mai Mohamed Eida
This paper investigates false positive constructions: grammatical structures which an LLM hallucinates as distinct constructions but which human introspection does not support. Bot…