{
  "id": 17023,
  "url": "https://arxiv.org/abs/2604.17359",
  "title": "Plausible Patients, Impossible Populations: Auditing Epidemiological Fidelity in Large Language Model Mental Health Simulations",
  "summary": "arXiv:2604.17359v2 Announce Type: replace Abstract: Language models asked to simulate psychiatric patients produce cases that survive inspection one at a time and populations that match no real one. We gave GPT-4o-mini, Gemini-3-Flash, DeepSeek-V3 and GLM-4.7 each of 120 demographic cohorts under two framings, one written as a clinician enters a patient and one as a person describes themselves, and scored all 28,800 responses against survey-weighted PHQ-8 anchors derived from NHANES microdata. C",
  "authors": "Patrick Keough",
  "category": "research",
  "topics": "healthcare,transparency",
  "orgs": "google,deepseek",
  "regions": null,
  "published_at": "2026-08-07T04:00:00.000Z",
  "fetched_at": "2026-08-07T05:10:58.501Z",
  "source_slug": "arxiv-cscy",
  "source_name": "arXiv cs.CY",
  "source_homepage": "https://arxiv.org/list/cs.CY/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/17023",
  "original_url": "https://arxiv.org/abs/2604.17359",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}