让医疗大模型生成可读性可控的文本，更易懂且不失专业。
MedReadCtrl: Personalizing medical text generation with readability-controlled instruction learning
- 通过指令微调控制输出文本复杂度，保持医学意图不变。
- 在9个数据集上显著优于GPT-4，低阅读水平用户偏好率达71.7%。
- 适合患者教育、医患沟通场景，助力公平获取AI医疗支持。
生成式AI在医疗领域展现出巨大潜力，从临床决策支持到面向患者的聊天机器人均能改善健康结果。部署中的关键挑战在于人机沟通效率，内容需兼具个性化与可理解性。本文提出MedReadCtrl，一种可读性可控的指令微调框架，使大模型能在不损失语义的前提下调整输出复杂度。在九个数据集和三个任务（涵盖医疗与通用领域）上的评估显示，MedReadCtrl在可读性指令遵循误差上显著优于GPT-4（如ReadMe数据集上为1.39 vs. 1.59，p<0.001），并在未见临床任务中取得显著提升（如MTSamples上ROUGE-L提高14.7，SARI提高6.18）。专家评估中，MedReadCtrl获得71.7%的偏好率，远超对照组23.3%，尤其在低识字水平用户中表现突出。该成果表明，MedReadCtrl能够将临床内容重构为可读性匹配、语义一致的表达，提供可扩展的解决方案，支持患者教育并促进公平的AI医疗普及。
原文摘要 · Abstract (English)
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.
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。