CLASS: A Design Framework for building Intelligent Tutoring Systems based on Learning Science principles
This work addresses the problem of creating more engaging and effective tutoring systems for students, though it appears incremental as it builds on existing LLM capabilities with a structured framework.
The authors tackled the challenge of building effective Intelligent Tutoring Systems (ITS) by introducing the CLASS framework, which uses curated datasets to enable step-by-step guidance and natural language interactions, resulting in a proof-of-concept ITS called SPOCK that received favorable expert feedback for its ability to break down biology questions and provide encouraging responses.
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 conversational dataset, CLASS assists ITS in facilitating natural language interactions, fostering engaging student-tutor conversations. The CLASS framework also provides valuable insights into ITS' internal decision-making process which allows seamless integration of user feedback, thus enabling continuous refinement and improvement. We also present a proof-of-concept ITS, referred to as SPOCK, which is trained using the CLASS framework with a focus on introductory college-level biology content. A carefully constructed protocol was developed for SPOCK's preliminary evaluation, examining aspects such as the factual accuracy and relevance of its responses. Experts in the field of biology offered favorable remarks, particularly highlighting SPOCK's capability to break down questions into manageable subproblems and provide encouraging responses to students. Code and models are available at https://github.com/luffycodes/Tutorbot-Spock.