No Reader Left Behind: Multi-Agent Summaries Everyone Can Understand

2026-04-12

AI Summary

This study addresses the challenge of generating summaries that meet the diverse readability needs of readers with varying language proficiency and cognitive abilities, particularly for complex texts such as government documents. The authors propose NRLB, a multi-agent framework that simulates three representative reader groups—elementary students, non-native speakers, and individuals with attention deficits—to automatically identify difficult vocabulary, supplement contextual information, and rephrase ambiguous constructions. By integrating template-driven summarization planning with iterative refinement based on simulated reader feedback, NRLB produces highly readable summaries while preserving factual accuracy. Experimental results demonstrate significant improvements in readability metrics across multiple datasets, and human evaluations show a 55%–76% preference rate, confirming the framework’s effectiveness in enhancing public accessibility without compromising content fidelity.

Abstract

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.

Problem

• plain language summarization
• readability
• cognitive barriers
• linguistic accessibility
• diverse readers

Innovation

• multi-agent summarization
• plain language
• readability
• reader-oriented refinement
• accessible NLP