# Iterative Prompt Refinement for Dyslexia-Friendly Text Summarization Using GPT-4o

arXiv: https://arxiv.org/abs/2602.22524 · HTML: https://mlsanity.com/paper/2602.22524/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 6 of 6)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [LaMPost: Design and Evaluation of an AI-assisted Email Writing Prototype for Adults with Dyslexia](https://mlsanity.com/paper/2207.02308/) (2022)
- [Generating Summaries with Controllable Readability Levels](https://mlsanity.com/paper/2310.10623/) (2023)
- [Readability Controllable Biomedical Document Summarization](https://mlsanity.com/paper/2210.04705/) (2022)
- [Let AI Read First: Enhancing Reading Abilities for Individuals with Dyslexia through Artificial Intelligence](https://mlsanity.com/paper/2504.00941/) (2025)

## Abstract (arXiv)

Dyslexia affects approximately 10% of the global population and presents persistent challenges in reading fluency and text comprehension. While existing assistive technologies address visual presentation, linguistic complexity remains a substantial barrier to equitable access. This paper presents an empirical study on dyslexia-friendly text summarization using an iterative prompt-based refinement pipeline built on GPT-4o. We evaluate the pipeline on approximately 2,000 news article samples, applying a readability target of Flesch Reading Ease >= 90. Results show that the majority of summaries meet the readability threshold within four attempts, with many succeeding on the first try. A composite score combining readability and semantic fidelity shows stable performance across the dataset, ranging from 0.13 to 0.73 with a typical value near 0.55. These findings establish an empirical baseline for accessibility-driven NLP summarization and motivate further human-centered evaluation with dyslexic readers.