# Generating Educational Materials with Different Levels of Readability using LLMs

arXiv: https://arxiv.org/abs/2406.12787 · HTML: https://mlsanity.com/paper/2406.12787/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 29 references that are in the map.
- First posted on arXiv 18 Jun 2024.

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

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Controllable Text Simplification with Explicit Paraphrasing](https://mlsanity.com/paper/2010.11004/) (2020)
- [From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting](https://mlsanity.com/paper/2309.04269/) (2023)
- [Explainable Prediction of Text Complexity: The Missing Preliminaries for Text Simplification](https://mlsanity.com/paper/2007.15823/) (2020)
- [Prototyping the use of Large Language Models (LLMs) for adult learning content creation at scale](https://mlsanity.com/paper/2306.01815/) (2023)

## Built on by (most cited first, 9 of 9)

- [TeachTune: Reviewing Pedagogical Agents Against Diverse Student Profiles with Simulated Students](https://mlsanity.com/paper/2410.04078/) (2024)
- [EduBench: A Comprehensive Benchmarking Dataset for Evaluating Large Language Models in Diverse Educational Scenarios](https://mlsanity.com/paper/2505.16160/) (2025)
- [Advancing Content Moderation: Evaluating Large Language Models for Detecting Sensitive Content Across Text, Images, and Videos](https://mlsanity.com/paper/2411.17123/) (2024)
- [Position: LLMs Can be Good Tutors in English Education](https://mlsanity.com/paper/2502.05467/) (2025)
- [Free-text Rationale Generation under Readability Level Control](https://mlsanity.com/paper/2407.01384/) (2024)
- [Education in the Era of Neurosymbolic AI](https://mlsanity.com/paper/2411.12763/) (2024)
- [A Generalizable Rhetorical Strategy Annotation Model Using LLM-based Debate Simulation and Labelling](https://mlsanity.com/paper/2510.15081/) (2025)
- [TACLA: An LLM-Based Multi-Agent Tool for Transactional Analysis Training in Education](https://mlsanity.com/paper/2510.17913/) (2025)
- [What Differentiates Educational Literature? A Multimodal Fusion Approach of Transformers and Computational Linguistics](https://mlsanity.com/paper/2411.17593/) (2024)

## Abstract (arXiv)

This study introduces the leveled-text generation task, aiming to rewrite educational materials to specific readability levels while preserving meaning. We assess the capability of GPT-3.5, LLaMA-2 70B, and Mixtral 8x7B, to generate content at various readability levels through zero-shot and few-shot prompting. Evaluating 100 processed educational materials reveals that few-shot prompting significantly improves performance in readability manipulation and information preservation. LLaMA-2 70B performs better in achieving the desired difficulty range, while GPT-3.5 maintains original meaning. However, manual inspection highlights concerns such as misinformation introduction and inconsistent edit distribution. These findings emphasize the need for further research to ensure the quality of generated educational content.