ReadEasy: Bridging Reading Accessibility Gaps using Responsible Multimodal Simplification with Generative AI

Sharv Murgai, Shivatmica Murgai

Track: Creative demo

Keywords: Text Simplification, Multimodal Learning, Retrieval-Augmented Generation, Graph-based Retrieval, Accessibility, Education Technology, Healthcare Communication, Technical Communication, Human-in-the-Loop Systems, Responsible AI

TL;DR: A multimodal, retrieval-augmented system that simplifies text and images with age-aware tuning, graph-based knowledge, and human feedback to make complex educational, healthcare, and technical content accessible.

Abstract:

We present readeasy.org, a multimodal, retrieval-augmented system that simplifies text and images
for improved accessibility in education, healthcare, and technical domains.
The system integrates Age-of-Acquisition guidance, word-sense disambiguation,
graph-based retrieval-augmented generation (RAG), image captioning,
and a human-in-the-loop feedback loop.
Across 14,000 items, it improves readability over GPT-4 baselines
(+22.21\% SARI, +14.11\% Flesch), increases domain retrieval precision (+11\%),
and yields further gains with user feedback (+8\% content relevance, +15\% satisfaction).
In classroom use with 200 K--12 students and additional professional cohorts,
users rated outputs as easier to understand and more useful.
This Creative Demo highlights how responsible AI design can support accessibility
while maintaining semantic integrity.

Submission Number: 65