Ask a large language model to judge your loan, job, or rental application, and being a white man without a college degree is the worst demographic card you can hold.
Researchers ran full-factorial tests on 18 models from 12 developer groups, feeding each one 32 synthetic applicant profiles that varied by gender, race, age, citizenship, and education while holding income, job history, and other financial details constant. Each model scored every profile ten times across three scenarios (credit, hiring, and rental housing), producing 17,280 ratings on a 0-100 scale. White men without degrees landed at the bottom in all three: 75.87 for credit, 92.71 for hiring, and 86.62 for rental housing. Black women with degrees scored highest, beating white men without degrees by 2.94, 3.66, and 3.56 points respectively.
Individually, being a woman, being Black, or holding a degree each nudged scores up across all three settings, but it's the stacking of disadvantages that hurts white men without degrees most. That group landed in the bottom two of eight groups in 46 of 54 model-scenario pairings tested, or 85.2 percent, meaning the pattern holds across nearly the entire field of models rather than one outlier's training data.
The result lines up with other research tracking rising economic and health strain among white men without degrees, a reminder that broad race and gender categories can mask real hardship just as easily as they can mask privilege.