{
  "id": 3634506,
  "title": "When Composition Doesn't Add Up: Humans Identifying Defects in AI-Generated Images",
  "url": "https://urgent.news/2026/08/26/when-composition-doesnt-add-up-humans-identifying-defects-in-ai",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-26T15:47:47.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.25933v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "*Chulin Zhao and Ruoqi Hu contributed equally to this work. State-of-the-art text-to-image (T2I) models exhibit pronounced and systematic defects when prompts involve intricate compositional factors such as multiple entities and multiple attributes. In this paper, we investigate how humans identify such defects. Specifically, we manually select 651 reference images from the four categories of…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}