{
  "id": 4409,
  "url": "https://arxiv.org/abs/2605.13113v1",
  "title": "Context Matters: Auditing Gender Bias in T2I Generation through Risk-Tiered Use-Case Profiles",
  "summary": "Text-to-image (T2I) generative models are increasingly used to produce content for education, media, and public-facing communication, and are starting to be integrated into higher-impact pipelines. Since generated images tend to reinforce stereotypes, producing representational erasure via \"default\" depictions and shaping perceptions of who belongs in certain roles, a growing body of work has proposed metrics to quantify gender bias in T2I outputs. Yet existing evaluations remain fragmented. Met",
  "authors": "Jose Luna, Yankun Wu, Xiaofei Xie, Noa Garcia",
  "category": "research",
  "topics": "bias-fairness,children-education,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-13T07:25:04.000Z",
  "fetched_at": "2026-07-14T16:30:59.236Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4409",
  "original_url": "https://arxiv.org/abs/2605.13113v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}