{
  "id": 3672,
  "url": "https://arxiv.org/abs/2606.28332v1",
  "title": "When Medical Safety Alignment Fails: A Benchmark for Evaluating LLMs on High-Risk Medical Queries",
  "summary": "Large language models (LLMs) are increasingly used for medical and health-related questions, yet their safety in high-risk medical scenarios remains poorly understood. We introduce \\textsc{MedHarm}\\footnote{Code and data will be released upon acceptance. Due to the sensitive nature of high-risk medical queries, data access will be available to qualified researchers upon request.}, a high-risk medical safety benchmark with 1,100 medically grounded queries across 10 safety-critical categories, inc",
  "authors": "Yige Li, Jun Sun, Wei Zhao, Zhe Li, Yutao Wu, Hanxun Huang et al.",
  "category": "research",
  "topics": "safety-alignment,healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-26T14:39:18.000Z",
  "fetched_at": "2026-07-14T16:30:27.607Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3672",
  "original_url": "https://arxiv.org/abs/2606.28332v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}