SimplifyMyText: An LLM-Based System for Inclusive Plain Language Text Simplification

2025-04-19

European Conference on Information Retrieval

AI Summary

To address accessibility challenges posed by complex texts for cognitively diverse populations, this paper introduces the first LLM-driven system for multi-level plain language simplification. Methodologically, it pioneers synergistic integration of GPT-4 and Llama-3, jointly guided by user profiling and cross-format inputs (text/documents), enabling dynamic, fine-grained, personalized simplification; multi-dimensional evaluation—assessing readability, faithfulness, conciseness, and inclusivity—informs prompt engineering and output calibration. Contributions include: (1) the first multi-model collaborative framework for plain language simplification; (2) an end-to-end system supporting user-profile-driven adaptation and format-agnostic processing; and (3) consistent superiority over baselines in both automated and human evaluations, significantly advancing information accessibility. The system is open-sourced and publicly deployed at simplifymytext.org.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Humans and AI: AI for Accessibility

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Text simplification is essential for making complex content accessible to diverse audiences who face comprehension challenges. Yet, the limited availability of simplified materials creates significant barriers to personal and professional growth and hinders social inclusion. Although researchers have explored various methods for automatic text simplification, none fully leverage large language models (LLMs) to offer tailored customization for different target groups and varying levels of simplicity. Moreover, despite its proven benefits for both consumers and organizations, the well-established practice of plain language remains underutilized. In this paper, we https://simplifymytext.org, the first system designed to produce plain language content from multiple input formats, including typed text and file uploads, with flexible customization options for diverse audiences. We employ GPT-4 and Llama-3 and evaluate outputs across multiple metrics. Overall, our work contributes to research on automatic text simplification and highlights the importance of tailored communication in promoting inclusivity.

Problem

• Lack of simplified materials hinders accessibility and inclusion
• Existing methods fail to customize simplification for diverse audiences
• Underutilization of plain language despite its proven benefits

Innovation

• LLM-based text simplification for diverse audiences
• Customizable plain language output from multiple inputs
• GPT-4 and Llama-3 for multi-metric evaluation