{
  "id": 6119,
  "url": "https://arxiv.org/abs/2604.08326v1",
  "title": "ProMedical: Hierarchical Fine-Grained Criteria Modeling for Medical LLM Alignment via Explicit Injection",
  "summary": "Aligning Large Language Models (LLMs) with high-stakes medical standards remains a significant challenge, primarily due to the dissonance between coarse-grained preference signals and the complex, multi-dimensional nature of clinical protocols. To bridge this gap, we introduce ProMedical, a unified alignment framework grounded in fine-grained clinical criteria. We first construct ProMedical-Preference-50k, a dataset generated via a human-in-the-loop pipeline that augments medical instructions wi",
  "authors": "He Geng, Yangmin Huang, Lixian Lai, Qianyun Du, Hui Chu, Zhiyang He et al.",
  "category": "research",
  "topics": "safety-alignment,healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-09T14:57:33.000Z",
  "fetched_at": "2026-07-14T16:32:15.636Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6119",
  "original_url": "https://arxiv.org/abs/2604.08326v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}