CLASS: A Design Framework for Building Intelligent Tutoring Systems Based on Learning Science principles

This paper presents CLASS, a design framework for building Intelligent Tutoring Systems using Large Language Models, and SPOCK, a proof-of-concept ITS for college-level biology that provides step-by-step guidance and conversational tutoring interactions grounded in learning science principles like scaffolding and socio-constructivist learning.

We present a design framework called Conversational Learning with Analytical Step-by-Step Strategies (CLASS) for building advanced Intelligent Tutoring Systems (ITS) powered by high-performance Large Language Models (LLMs). The CLASS framework empowers ITS with two key capabilities. First, through a carefully curated scaffolding dataset, CLASS equips ITS with essential problem-solving strategies, enabling it to provide tutor-like, step-by-step guidance to students. Second, by using a dynamic con

Study Type

Source

Framework Categories

Tool Types

Tags