arXiv 2507.074192025-07-10cs.CLcs.AI

MedReadCtrl：通过可读性控制的指令学习实现医疗文本生成的个性化

MedReadCtrl: Personalizing medical text generation with readability-controlled instruction learning

Center for Healthcare Organization and Implementation Research（医疗组织与实施研究中心）；VA Bedford Health Care（贝福德医疗中心）；Miner School of Computer and Information Sciences（米纳尔计算机与信息科学学院）；University of Massachusetts Medical School（马萨诸塞大学医学学院）；School of Nursing（护理学院）；Zuckerberg College of Health Sciences（泽克伯格健康科学学院）

Hieu Tran, Zonghai Yao, Won Seok Jang, Sharmin Sultana, Allen Chang, Yuan Zhang, Hong Yu

备注：: Equal contribution for the first two authors. arXiv admin note: text overlap with arXiv:2406.09205

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出可读性控制的指令微调框架MedReadCtrl，使LLMs在不损害语义下调整输出复杂度，在多项任务中显著降低可读性指令遵循错误并获专家高度偏好，为患者教育提供可扩展方案。

摘要：

生成式AI在医疗保健领域展现了强大潜力，从临床决策支持到改善预后的面向患者聊天机器人。部署面临的关键挑战是有效的人机通信，内容必须兼具个性化与可理解性。我们提出了MedReadCtrl，一个可读性控制的指令微调框架，使LLMs能在不损害语义的情况下调整输出复杂度。跨医疗和通用领域的9个数据集与3项任务的评估显示，MedReadCtrl的可读性指令遵循错误显著低于GPT-4（例如，在ReadMe上为1.39对1.59，p<0.001），并在未见临床任务上取得大幅提升（例如，在MTSamples上ROUGE-L提升14.7，SARI提升6.18）。专家一致更偏好MedReadCtrl（71.7%对23.3%），尤其是在低文化水平下。这些提升反映了MedReadCtrl将临床内容重构为易懂且符合可读性要求语言的能力，同时保留了医疗意图，为支持患者教育和扩大AI赋能医疗的公平获取提供了可扩展方案。

英文摘要：

Generative AI has demonstrated strong potential in healthcare, from clinical decision support to patient-facing chatbots that improve outcomes. A critical challenge for deployment is effective human-AI communication, where content must be both personalized and understandable. We introduce MedReadCtrl, a readability-controlled instruction tuning framework that enables LLMs to adjust output complexity without compromising meaning. Evaluations of nine datasets and three tasks across medical and general domains show that MedReadCtrl achieves significantly lower readability instruction-following errors than GPT-4 (e.g., 1.39 vs. 1.59 on ReadMe, p<0.001) and delivers substantial gains on unseen clinical tasks (e.g., +14.7 ROUGE-L, +6.18 SARI on MTSamples). Experts consistently preferred MedReadCtrl (71.7% vs. 23.3%), especially at low literacy levels. These gains reflect MedReadCtrl's ability to restructure clinical content into accessible, readability-aligned language while preserving medical intent, offering a scalable solution to support patient education and expand equitable access to AI-enabled care.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。