{
  "id": 5222,
  "url": "https://arxiv.org/abs/2604.26577v1",
  "title": "Benchmarking the Safety of Large Language Models for Robotic Health Attendant Control",
  "summary": "Large language models (LLMs) are increasingly considered for deployment as the control component of robotic health attendants, yet their safety in this context remains poorly characterized. We introduce a dataset of 270 harmful instructions spanning nine prohibited behavior categories grounded in the American Medical Association Principles of Medical Ethics, and use it to evaluate 72 LLMs in a simulation environment based on the Robotic Health Attendant framework. The mean violation rate across ",
  "authors": "Mahiro Nakao, Kazuhiro Takemoto",
  "category": "research",
  "topics": "healthcare,agents-autonomy,environment",
  "orgs": null,
  "regions": "us",
  "published_at": "2026-04-29T11:58:59.000Z",
  "fetched_at": "2026-07-14T16:31:35.575Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5222",
  "original_url": "https://arxiv.org/abs/2604.26577v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}