Generative Students: Using LLM-Simulated Student Profiles to Support Question Item Evaluation

Abstract

Figure 1: The design of the prompt architecture of Generative Students is based on the KLI framework, which uses knowledge components (KCs) to define the elements students are expected to learn.With the KCs identified for a given task (a), the generative student's profile is a function of the list of KCs the student has mastered, has confusion about, or has no evidence of knowledge of (b).Users can define master prompt, confusion prompt, and unknown prompt for a given task (c).This architecture thus supports automatic creation of diverse student profiles (d).

Topics & Concepts