How Teachers Can Use Large Language Models and Bloom's Taxonomy to Create Educational Quizzes
This addresses the need for pedagogically sound question generation in education, though it is incremental by building on existing methods with teacher input.
The paper tackled the problem of generating educational quizzes by applying a large language model with Bloom's taxonomy, finding that teachers prefer using automatically generated questions with no loss in quality and even some improvements in quiz quality.
Question generation (QG) is a natural language processing task with an abundance of potential benefits and use cases in the educational domain. In order for this potential to be realized, QG systems must be designed and validated with pedagogical needs in mind. However, little research has assessed or designed QG approaches with the input from real teachers or students. This paper applies a large language model-based QG approach where questions are generated with learning goals derived from Bloom's taxonomy. The automatically generated questions are used in multiple experiments designed to assess how teachers use them in practice. The results demonstrate that teachers prefer to write quizzes with automatically generated questions, and that such quizzes have no loss in quality compared to handwritten versions. Further, several metrics indicate that automatically generated questions can even improve the quality of the quizzes created, showing the promise for large scale use of QG in the classroom setting.