Leveraging In-Context Learning and Retrieval-Augmented Generation for Automatic Question Generation in Educational Domains
This addresses the time-consuming and cognitively demanding task of creating pedagogically sound questions for educational domains, but it is incremental as it builds on existing methods like ICL and RAG.
The paper tackled the problem of automated question generation in education, which often produces out-of-context questions, by exploring In-Context Learning, Retrieval-Augmented Generation, and a novel Hybrid Model; the results showed that the ICL approach and Hybrid Model consistently outperformed other methods in generating contextually accurate and relevant questions.
Question generation in education is a time-consuming and cognitively demanding task, as it requires creating questions that are both contextually relevant and pedagogically sound. Current automated question generation methods often generate questions that are out of context. In this work, we explore advanced techniques for automated question generation in educational contexts, focusing on In-Context Learning (ICL), Retrieval-Augmented Generation (RAG), and a novel Hybrid Model that merges both methods. We implement GPT-4 for ICL using few-shot examples and BART with a retrieval module for RAG. The Hybrid Model combines RAG and ICL to address these issues and improve question quality. Evaluation is conducted using automated metrics, followed by human evaluation metrics. Our results show that both the ICL approach and the Hybrid Model consistently outperform other methods, including baseline models, by generating more contextually accurate and relevant questions.