{
  "id": 5319,
  "url": "https://arxiv.org/abs/2604.24186v1",
  "title": "MultiDx: A Multi-Source Knowledge Integration Framework towards Diagnostic Reasoning",
  "summary": "Diagnostic prediction and clinical reasoning are critical tasks in healthcare applications. While Large Language Models (LLMs) have shown strong capabilities in commonsense reasoning, they still struggle with diagnostic reasoning due to limited domain knowledge. Existing approaches often rely on internal model knowledge or static knowledge bases, resulting in knowledge insufficiency and limited adaptability, which hinder their capacity to perform diagnostic reasoning. Moreover, these methods foc",
  "authors": "Yimin Deng, Zhenxi Lin, Yejing Wang, Guoshuai Zhao, Pengyue Jia, Zichuan Fu et al.",
  "category": "research",
  "topics": "healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-27T08:46:29.000Z",
  "fetched_at": "2026-07-14T16:31:40.220Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5319",
  "original_url": "https://arxiv.org/abs/2604.24186v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}