让政府文件人人都能看懂，用多角色模拟提升摘要可读性
No Reader Left Behind: Multi-Agent Summaries Everyone Can Understand
- 模拟学生、非母语者、注意力缺陷三类读者，动态优化语言
- 在多个数据集上显著提升可读性，准确率保持不变
- 适合政策传播、公共信息简化等需要普适可读性的场景
美国《清晰书写法案》要求政府文件使用公众易懂的简明语言，但现有摘要系统难以应对读者间多样化的语言与认知障碍。本文提出NRLB（No Reader Left Behind）多智能体框架，模拟三类代表性读者：小学生、非母语读者及注意力缺陷读者。NRLB结合模板化规划与迭代式读者导向优化，系统识别并解决难词、缺失背景和混乱句式问题。跨多个数据集的评估显示，其在保持事实准确性的同时持续提升可读性。人工评估进一步验证其效果，标注者偏好率介于55%至76%，表明NRLB能生成既忠实原文又广泛可及的简明摘要。
原文摘要 · Abstract (English)
The Plain Writing Act in the United States requires government documents to be accessible in clear and simple language that the general public can easily understand, yet existing summarization systems struggle to address diverse linguistic and cognitive barriers among general readers. We present NRLB (No Reader Left Behind), a multi-agent framework for plain language summarization that simulates three representative reader groups: elementary school student readers, non-native readers, and readers with attention deficits. NRLB combines template-based planning with iterative, reader-oriented refinement, enabling systematic detection and resolution of difficult terms, missing contexts, and confusing sentences. Evaluations across multiple datasets demonstrate consistent improvements in readability while preserving factual accuracy. Human evaluation further validates NRLB's impact, with annotator preference rates ranging from 55% to 76%, highlighting NRLB's potential to produce plain language summaries that are both faithful to the source and broadly accessible to the general public.
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。