mlsanityData to 7 Oct 2026

Generating Educational Materials with Different Levels of Readability using LLMs

arXiv 2406.12787 ↗First posted 18 Jun 2024cs.CL cs.HCcited by 9

Not on the map. Why?

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.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 6 of its 29 references that are in the map. First posted on arXiv 18 Jun 2024.

Builds on

6 of 29 references.

References · 6

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  3. 2020Controllable Text Simplification with Explicit Paraphrasingcited by 53
  4. 2023From Sparse to Dense: GPT-4 Summarization with Chain of Density Promptingcited by 52
  5. 2020Explainable Prediction of Text Complexity: The Missing Preliminaries for Text Simplificationcited by 12
  6. 2023Prototyping the use of Large Language Models (LLMs) for adult learning content creation at scalecited by 12

Built on by

Cited by year

Citing papers per year: 2024: 5; 2025: 4.

9 papers.

  1. 2024TeachTune: Reviewing Pedagogical Agents Against Diverse Student Profiles with Simulated Studentscited by 25
  2. 2025EduBench: A Comprehensive Benchmarking Dataset for Evaluating Large Language Models in Diverse Educational Scenarioscited by 16
  3. 2024Advancing Content Moderation: Evaluating Large Language Models for Detecting Sensitive Content Across Text, Images, and Videoscited by 10
  4. 2025Position: LLMs Can be Good Tutors in English Educationcited by 6
  5. 2024Free-text Rationale Generation under Readability Level Controlcited by 4
  6. 2024Education in the Era of Neurosymbolic AIcited by 4
  7. 2025A Generalizable Rhetorical Strategy Annotation Model Using LLM-based Debate Simulation and Labellingcited by 1
  8. 2025TACLA: An LLM-Based Multi-Agent Tool for Transactional Analysis Training in Educationcited by 1
  9. 2024What Differentiates Educational Literature? A Multimodal Fusion Approach of Transformers and Computational Linguisticscited by 0