Comparison of Large Language Models for Generating Contextually Relevant Questions
It addresses the problem of automating question generation for educational applications, but is incremental as it compares existing models on a specific task.
This study compared three large language models for generating contextually relevant questions from university slide text without fine-tuning, finding that GPT-3.5 and Llama 2-Chat 13B slightly outperformed Flan T5 XXL, with GPT-3.5 excelling in tailoring questions to match input answers based on student evaluations of 246 questions.
This study explores the effectiveness of Large Language Models (LLMs) for Automatic Question Generation in educational settings. Three LLMs are compared in their ability to create questions from university slide text without fine-tuning. Questions were obtained in a two-step pipeline: first, answer phrases were extracted from slides using Llama 2-Chat 13B; then, the three models generated questions for each answer. To analyze whether the questions would be suitable in educational applications for students, a survey was conducted with 46 students who evaluated a total of 246 questions across five metrics: clarity, relevance, difficulty, slide relation, and question-answer alignment. Results indicate that GPT-3.5 and Llama 2-Chat 13B outperform Flan T5 XXL by a small margin, particularly in terms of clarity and question-answer alignment. GPT-3.5 especially excels at tailoring questions to match the input answers. The contribution of this research is the analysis of the capacity of LLMs for Automatic Question Generation in education.