文献类型：会议论文

英文题名：LCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Review

作者：Yuan, Cheng[1];Rui, Xinkai[1,2];Fan, Yongqi[1];Fan, Yawei[1];Zhong, Boyang[1];Wang, Jiacheng[1];Zhang, Weiyan[1];Ruan, Tong[1]

机构：[1]East China Univ Sci & Technol, Shanghai 200237, Peoples R China;[2]Shanghai Jiao Tong Univ, Ruijin Hosp, Sch Med, Shanghai 200025, Peoples R China

会议论文集：63rd Association for Computational Linguistics Meeting-ACL-Annual

会议日期：JUL 27-AUG 01, 2025

会议地点：Vienna, AUSTRIA

语种：英文

摘要：Despite the remarkable performance of Large Language Models (LLMs) in automated discharge summary generation, they still suffer from hallucination issues, such as generating inaccurate content or fabricating information without valid sources. In addition, electronic medical records (EMRs) typically consist of long-form data, making it challenging for LLMs to attribute the generated content to the sources. To address these challenges, we propose LCDS, a Logic-Controlled Discharge Summary generation system. LCDS constructs a source mapping table by calculating textual similarity between EMRs and discharge summaries to constrain the scope of summarized content. Moreover, LCDS incorporates a comprehensive set of logical rules, enabling it to generate more reliable silver discharge summaries tailored to different clinical fields. Furthermore, LCDS supports source attribution for generated content, allowing experts to efficiently review, provide feedback, and rectify errors. The resulting golden discharge summaries are subsequently recorded for incremental fine-tuning of LLMs. Our project and demo video are in the GitHub repository https://github.com/ycycyc02/LCDS.