Generative AI technologies such as large language models show novel potential to enhance educational research. For example, generative large language models were shown to be capable of solving quantitative reasoning tasks in physics and concept tests such as the Force Concept Inventory (FCI). Given the importance of such concept inventories for…

The Force Concept Inventory is a multiple-choice test and is one of the most popular and most analyzed concept inventories. It is used to investigate student understanding of Newtonian mechanics. A structured approach to data analysis can transform it in a "diagnostic" instrument that can validate inferences about student thinking. In…