{"ID":2880867,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.15845","arxiv_id":"2508.15845","title":"Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reports","abstract":"The manual creation of the \"Impression\" section in radiology reports is a primary driver of radiologist burnout. To address this challenge, we propose a coarse-to-fine framework that leverages open-source large language models (LLMs) to automatically generate and personalize impressions from clinical findings. The system first produces a draft impression and then refines it using machine learning and reinforcement learning from human feedback (RLHF) to align with individual radiologists' styles while ensuring factual accuracy. We fine-tune LLaMA and Mistral models on a large dataset of reports from the University of Chicago Medicine. Our approach is designed to significantly reduce administrative workload and improve reporting efficiency while maintaining high standards of clinical precision.","short_abstract":"The manual creation of the \"Impression\" section in radiology reports is a primary driver of radiologist burnout. To address this challenge, we propose a coarse-to-fine framework that leverages open-source large language models (LLMs) to automatically generate and personalize impressions from clinical findings. The syst...","url_abs":"https://arxiv.org/abs/2508.15845","url_pdf":"https://arxiv.org/pdf/2508.15845v2","authors":"[\"Chengbo Sun\",\"Hui Yi Leong\",\"Lei Li\"]","published":"2025-08-19T20:54:40Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\",\"RLHF\"]","has_code":false}