Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Empowering Personalized Learning through a Conversation-based Tutoring System with Student Modeling

Minju Park, Sojung Kim, Seunghyun Lee, Soonwoo Kwon, Kyuseok Kim

TL;DR

Design considerations for a personalized tutoring system that involves a student modeling with diagnostic components, and a conversation-based tutor utilizing LLM with prompt engineering that incorporates student assessment outcomes and various instructional strategies are discussed.

Abstract

As the recent Large Language Models(LLM's) become increasingly competent in zero-shot and few-shot reasoning across various domains, educators are showing a growing interest in leveraging these LLM's in conversation-based tutoring systems. However, building a conversation-based personalized tutoring system poses considerable challenges in accurately assessing the student and strategically incorporating the assessment into teaching within the conversation. In this paper, we discuss design considerations for a personalized tutoring system that involves the following two key components: (1) a student modeling with diagnostic components, and (2) a conversation-based tutor utilizing LLM with prompt engineering that incorporates student assessment outcomes and various instructional strategies. Based on these design considerations, we created a proof-of-concept tutoring system focused on personalization and tested it with 20 participants. The results substantiate that our system's framework facilitates personalization, with particular emphasis on the elements constituting student modeling. A web demo of our system is available at http://rlearning-its.com.

Empowering Personalized Learning through a Conversation-based Tutoring System with Student Modeling

TL;DR

Design considerations for a personalized tutoring system that involves a student modeling with diagnostic components, and a conversation-based tutor utilizing LLM with prompt engineering that incorporates student assessment outcomes and various instructional strategies are discussed.

Abstract

As the recent Large Language Models(LLM's) become increasingly competent in zero-shot and few-shot reasoning across various domains, educators are showing a growing interest in leveraging these LLM's in conversation-based tutoring systems. However, building a conversation-based personalized tutoring system poses considerable challenges in accurately assessing the student and strategically incorporating the assessment into teaching within the conversation. In this paper, we discuss design considerations for a personalized tutoring system that involves the following two key components: (1) a student modeling with diagnostic components, and (2) a conversation-based tutor utilizing LLM with prompt engineering that incorporates student assessment outcomes and various instructional strategies. Based on these design considerations, we created a proof-of-concept tutoring system focused on personalization and tested it with 20 participants. The results substantiate that our system's framework facilitates personalization, with particular emphasis on the elements constituting student modeling. A web demo of our system is available at http://rlearning-its.com.
Paper Structure (23 sections, 1 equation, 3 figures, 1 table)

This paper contains 23 sections, 1 equation, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Intelligent Tutoring Systems
  4. Cognitive Diagnostic Modeling
  5. Design of Personalized Tutoring System
  6. Student Assessment
  7. Cognitive State
  8. Affective State
  9. Learning Style
  10. LLM Prompt-Based Personalized Tutoring System
  11. Adaptive Exercise Selection
  12. Prompt Design for Personalized Tutoring
  13. Results
  14. Observation
  15. Discussion
  16. ...and 8 more sections

Figures (3)

  • Figure 1: Overview of our proof-of-concept personalized tutoring system
  • Figure 2: Cyclical framework and structure of the system prompt in our proof-of-concept personalized tutoring system
  • Figure 3: (a) Counts of labeled tutor actions across entire dialogues. (b) Distribution of the ratio of each tutor action computed on a student-wise basis.