{
  "id": 13592,
  "url": "https://arxiv.org/abs/2604.00024",
  "title": "WHBench: Evaluating Frontier LLMs with Expert-in-the-Loop Validation on Women's Health Topics",
  "summary": "arXiv:2604.00024v2 Announce Type: replace-cross Abstract: Large language models are increasingly used for medical guidance, but women's health remains under-evaluated in benchmark design. We present the Women's Health Benchmark (WHBench), a targeted evaluation suite of 47 expert-crafted scenarios across 10 women's health topics, designed to expose clinically meaningful failure modes including outdated guidelines, unsafe omissions, dosing errors, and equity-related blind spots. We evaluate 22 mod",
  "authors": "Sneha Maurya, Spandana Govindgari, Girish Kumar, Akhara AI",
  "category": "research",
  "topics": "bias-fairness,healthcare",
  "orgs": null,
  "regions": null,
  "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/13592",
  "original_url": "https://arxiv.org/abs/2604.00024",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}