Large language models such as GPT-5 and Llama systematically rate speakers of German dialects less favorably than those using Standard German. This is shown by a recent collaborative study between Johannes Gutenberg University Mainz (JGU) and the universities of Hamburg and Washington, in which Professor Katharina von der Wense and Minh Duc Bui of JGU played a leading role.
AI language models show bias against regional German dialects
Reader’s Picks
-
A new study challenges common assumptions about loneliness in young adulthood, finding that feelings of disconnection can coexist with rich, [...]
-
A new analysis suggests that some developing countries have unexpectedly large numbers of childfree people; that is, people who have [...]
-
“Time flies,” “time waits for no one,” “as time goes on”: The way we speak about time tends to strongly [...]