Jing Wei
Jing Wei has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Chieh-Yang Huang
College of Information Sciences and Technology, Pennsylvania State University, United States
1 shared publication - Ting-Hao Kenneth Huang
Pennsylvania State University
1 shared publication
Latest Publications
- Open Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 16-22
Generating Educational Materials with Different Levels of Readability using LLMs
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.
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 16-22
Open AccessGenerating Educational Materials with Different Levels of Readability using LLMs
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.