Stay Hungry, Stay Foolish: On the Extended Reading Articles Generation with LLMs
Yow-Fu Liou, Yu-Chien Tang, An-Zi Yen
TL;DR
The study addresses the challenge of creating extended reading materials by leveraging large language models to generate enriched Dig Deeper articles from TED-Ed video transcripts and connect them to relevant courses. It introduces a three-stage pipeline: (1) initial Dig Deeper generation from transcripts, (2) semantic similarity-based ranking to select candidate lessons with an LLM-based evaluation, and (3) final refinement that weaves selected lessons and keywords into a cohesive article. Quantitative analyses compare two LLMs across hit rate, semantic similarity, and coherence, revealing trade-offs between diversity and depth, with Ablation studies highlighting the benefits of generation for coherence and potential hit-rate gains when generation steps are modified. The work demonstrates a viable path to automate generation and recommendation of supplementary educational content, potentially reducing educator workload and enriching student learning with contextually linked resources.
Abstract
The process of creating educational materials is both time-consuming and demanding for educators. This research explores the potential of Large Language Models (LLMs) to streamline this task by automating the generation of extended reading materials and relevant course suggestions. Using the TED-Ed Dig Deeper sections as an initial exploration, we investigate how supplementary articles can be enriched with contextual knowledge and connected to additional learning resources. Our method begins by generating extended articles from video transcripts, leveraging LLMs to include historical insights, cultural examples, and illustrative anecdotes. A recommendation system employing semantic similarity ranking identifies related courses, followed by an LLM-based refinement process to enhance relevance. The final articles are tailored to seamlessly integrate these recommendations, ensuring they remain cohesive and informative. Experimental evaluations demonstrate that our model produces high-quality content and accurate course suggestions, assessed through metrics such as Hit Rate, semantic similarity, and coherence. Our experimental analysis highlight the nuanced differences between the generated and existing materials, underscoring the model's capacity to offer more engaging and accessible learning experiences. This study showcases how LLMs can bridge the gap between core content and supplementary learning, providing students with additional recommended resources while also assisting teachers in designing educational materials.