Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.05319 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916831489425408 |
|---|---|
| author | Yuan, Cheng Rui, Xinkai Fan, Yongqi Fan, Yawei Zhong, Boyang Wang, Jiacheng Zhang, Weiyan Ruan, Tong |
| author_facet | Yuan, Cheng Rui, Xinkai Fan, Yongqi Fan, Yawei Zhong, Boyang Wang, Jiacheng Zhang, Weiyan Ruan, Tong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05319 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Review Yuan, Cheng Rui, Xinkai Fan, Yongqi Fan, Yawei Zhong, Boyang Wang, Jiacheng Zhang, Weiyan Ruan, Tong Computation and Language Artificial Intelligence 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. |
| title | LCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Review |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2507.05319 |