{
  "id": 18657,
  "url": "https://arxiv.org/abs/2608.10964v1",
  "title": "CARE: Confidence-Aware Reasoning for Reliable Medical VQA",
  "summary": "Reinforcement Fine-Tuning (RFT) has enabled medical Multimodal Large Language Models (MLLMs) to produce Chain-of-Thought (CoT) reasoning for visual question answering, yet these models suffer from $\\textit{confidence miscalibration}$---a systematic gap between expressed certainty and actual diagnostic accuracy that undermines clinical trust. We propose $\\textbf{CARE}$, a $\\textbf{C}$onfidence-$\\textbf{A}$ware medical $\\textbf{RE}$asoning framework that jointly optimizes accuracy and calibration",
  "authors": "Yuetian Du, Yucheng Wang, Zhenyuan Chen, Luyuan Chen, Rongyu Zhang, Jinjian Zhang, Wei Zhou, Zhijie Xu, Ming Kong, Zhan Zhou, Jie Liu, Qiang Zhu",
  "category": "research",
  "topics": "healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-11T14:28:52.000Z",
  "fetched_at": "2026-08-12T05:10:43.828Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/18657",
  "original_url": "https://arxiv.org/abs/2608.10964v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}