{
  "id": 13593,
  "url": "https://arxiv.org/abs/2604.26577",
  "title": "Benchmarking the Safety of Large Language Models for Robotic Health Attendant Control",
  "summary": "arXiv:2604.26577v2 Announce Type: replace-cross Abstract: 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 H",
  "authors": "Mahiro Nakao, Kazuhiro Takemoto",
  "category": "research",
  "topics": "healthcare,agents-autonomy,environment",
  "orgs": null,
  "regions": "us",
  "published_at": "2026-07-27T04:00:00.000Z",
  "fetched_at": "2026-07-27T05:10:06.638Z",
  "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/13593",
  "original_url": "https://arxiv.org/abs/2604.26577",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}