用逻辑规则控制生成，让病历摘要可溯源、易纠错。
LCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Review
- 通过文本相似度构建源数据映射表，限定摘要内容范围。
- 生成可溯源的摘要，支持专家高效审查与修正。
- 适合医疗AI开发、临床研究者及病历质量审核人员。
尽管大型语言模型在自动化出院摘要生成中表现卓越，但仍存在幻觉问题，如生成不准确内容或无依据编造信息。此外，电子病历通常为长篇文档，导致语言模型难以将生成内容与原始来源对应。为此，我们提出LCDS——一种逻辑控制的出院摘要生成系统。该系统通过计算电子病历与摘要间的文本相似度，构建源映射表，以限制摘要内容范围。同时，引入一套完整的逻辑规则，生成更可靠的银质摘要，适用于不同临床领域。此外，系统支持生成内容的来源追溯，使专家能够高效审查、反馈并修正错误。最终生成的黄金标准摘要用于增量微调语言模型。项目与演示视频见GitHub：https://github.com/ycycyc02/LCDS。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。