[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-ai-models-rate-white-men-without-degrees-lowest-study-finds":10,"sections":41},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":30,"tags":31,"sources":36,"feedback":40,"feedback_at":22,"cost_usd":40,"total_tokens":40},9601,"ai-models-rate-white-men-without-degrees-lowest-study-finds","AI Models Rate White Men Without Degrees Lowest, Study Finds","Eighteen AI models graded loan, job, and rental applications, and white men without degrees came out worst most often.","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.\n\nResearchers 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.\n\nIndividually, 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.\n\nThe 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.","[\"ai bias\",\"llm research\",\"hiring\",\"credit scoring\"]","2026-10-02T04:00:00.000Z","2026-10-03T02:26:57.802Z","2026-10-03T02:27:02.763Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"The 46-of-54 (85%) figure actually describes white men without degrees ranking lowest-or-second-lowest across model-scenario combinations, but the draft reattaches it to a claim about Black women scoring highest, and separately overstates 'White men...came out lowest in all three categories' as a flat ranking when the source's 46\u002F54 stat explicitly includes 'or second-lowest' — fix the misattribution and restore that nuance.","resolved","ai",[32,33,34,35],"ai bias","llm research","hiring","credit scoring",[37],{"name":38,"url":39},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.00185",0,{"sections":42},[43,46,50,54,59,63,67,72,77,82,87,92,97,102],{"name":44,"slug":30,"count":45,"latest_published_at":18},"AI",5896,{"name":47,"slug":48,"count":49,"latest_published_at":18},"Security","security",837,{"name":51,"slug":52,"count":53,"latest_published_at":18},"Policy","policy",438,{"name":55,"slug":56,"count":57,"latest_published_at":58},"Deals","deals",317,"2026-10-01T22:00:00.000Z",{"name":60,"slug":61,"count":62,"latest_published_at":18},"Hardware","hardware",199,{"name":64,"slug":65,"count":66,"latest_published_at":18},"Science","science",171,{"name":68,"slug":69,"count":70,"latest_published_at":71},"Consumer Tech","consumer-tech",155,"2026-10-01T19:54:10.000Z",{"name":73,"slug":74,"count":75,"latest_published_at":76},"Dev Tools","dev-tools",96,"2026-10-01T16:57:03.000Z",{"name":78,"slug":79,"count":80,"latest_published_at":81},"Software","software",93,"2026-09-30T21:41:11.000Z",{"name":83,"slug":84,"count":85,"latest_published_at":86},"Startups","startups",90,"2026-10-01T21:55:22.000Z",{"name":88,"slug":89,"count":90,"latest_published_at":91},"Gaming","gaming",53,"2026-10-02T02:50:39.000Z",{"name":93,"slug":94,"count":95,"latest_published_at":96},"General","general",50,"2026-09-30T21:37:54.000Z",{"name":98,"slug":99,"count":100,"latest_published_at":101},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":103,"slug":104,"count":105,"latest_published_at":106},"How-To","how-to",7,"2026-10-01T09:00:00.000Z"]