{
  "id": 5072,
  "url": "https://arxiv.org/abs/2605.13866v1",
  "title": "AI Alignment Amplifies the Role of Race, Gender, and Disability in Hiring Decisions",
  "summary": "Humans increasingly delegate decisions to language models, yet whether these systems reproduce or reshape human patterns of discrimination remains unclear. Here we run a large-scale study to analyse whether language models use demographic information in hiring decisions. We show, across 27 models and 177 occupations, that language models give female and Black candidates hiring advantages relative to otherwise-comparable male and white candidates, while giving disabled candidates disadvantages. T",
  "authors": "Ze Wang, Guobin Shen, Michael Thaler",
  "category": "research",
  "topics": "bias-fairness,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-02T16:08:07.000Z",
  "fetched_at": "2026-07-14T16:31:31.209Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5072",
  "original_url": "https://arxiv.org/abs/2605.13866v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}