{
  "id": 1305,
  "url": "https://arxiv.org/abs/2606.08483v1",
  "title": "Testing the Black Box: Structural Barriers to Independent Evaluation of Consumer-Facing Health LLMs",
  "summary": "Background: Consumer-facing large language models are now a common source of health information, and they interpret and personalize responses rather than retrieve them. Whether their responses vary across users is a clinical, equity, and governance question, sharpened by evidence that sycophantic responses can alter judgment and increase trust. Objective: To evaluate response variation and sycophancy in consumer-facing health LLMs under conditions resembling ordinary patient use. Methods: We con",
  "authors": "Rahul Gorijavolu, Kaushik Madapati, Pritika Vig, Rawan Abulibdeh, Nikhil Jaiswal, Mahri Kadyrova et al.",
  "category": "research",
  "topics": "bias-fairness,regulation,healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-07T07:01:15.000Z",
  "fetched_at": "2026-07-14T14:15:12.455Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/1305",
  "original_url": "https://arxiv.org/abs/2606.08483v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}