Information

Overview

Recent advances in generative AI, in particular deep generative and large language models like ChatGPT, are having transformational effects on the educational landscape. On the one hand, these advances provide unprecedented opportunities to enhance education by creating unique human-machine collaborative systems. For instance, these models could act as personalized digital tutors for students, as digital assistants for educators, and as digital peers to enable new collaborative learning scenarios. On the other hand, the advanced capabilities of these generative AI models have brought unexpected challenges for educators and policymakers worldwide. For instance, these advances have caused a chaotic disruption in universities and schools to design regulatory policies about the usage of these models and to educate both students and instructors about their strengths and limitations.

The goal of the GAIED (pronounced "guide") tutorial is to provide an overview of the research opportunities and challenges in applying generative AI methods for improving education. The tutorial will investigate these opportunities and challenges in education by focusing on two thrusts: (i) GAI→ED, i.e., exploring how recent advances in generative AI provide new opportunities to drastically improve state-of-the-art educational technology.; (ii) ED→GAI, i.e., identifying unique challenges in education that require safeguards along with technical innovations in generative AI.

Content

The technical content of the tutorial will primarily cover the domain of computing education, in particular, focusing on generative AI-powered educational technology for computational thinking and programming. Below, we provide an outline of the tutorial's content.

  1. Motivation and New Opportunities for Generative AI-Powered Education
    References: [1,2,3,4]
  2. Generative AI-Powered Expert Agents for Feedback Generation
    References: [5,6,7,8,9,10]
  3. Generative AI-Powered Expert Agents for Task Synthesis
    References: [11,12,13,8,14,15,16]
  4. Generative AI-Powered Student Agents for Simulating Behavior
    References: [9,17]
  5. Generative AI-Powered Student Agents for Learning by Teaching
    References: [18,19,20]
  6. Key Research Directions and Discussion
    References: [1]

References

  1. Generative AI for Education (GAIED): Advances, Opportunities, and Challenges
    by Denny et al., Survey 2024.
  2. An Analysis through an Equity Lens of the Implementation of Computer Science in K-8 Classrooms in a Large, Urban School District
    by Salac et al., SIGCSE 2019.
  3. Evaluating Large Language Models Trained on Code
    by Chen et al., Preprint 2021.
  4. GPT-4 Technical Report
    by OpenAI team, Preprint 2023.
  5. Using Large Language Models to Enhance Programming Error Messages
    by Leinonen et al., SIGCSE 2023.
  6. Generating High-Precision Feedback for Programming Syntax Errors using Large Language Models
    by Phung et al., EDM 2023.
  7. A Large Scale RCT on Effective Error Messages in CS1
    by Wang et al., SIGCSE 2024.
  8. Generative AI for Programming Education: Benchmarking ChatGPT, GPT-4, and Human Tutors
    by Phung et al., ICER Poster 2023.
  9. Automating Human Tutor-Style Programming Feedback: Leveraging GPT-4 Tutor Model for Hint Generation and GPT-3.5 Student Model for Hint Validation
    by Phung et al., LAK 2024.
  10. Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation
    by Kotalwar et al., Preprint 2024.
  11. Automatic Generation of Programming Exercises and Code Explanations Using Large Language Models
    by Sarsa et al., ICER 2022.
  12. Automated Distractor and Feedback Generation for Math Multiple-choice Questions via In-context Learning
    by McNichols et al., NeurIPS GAIED Workshop 2023.
  13. WordPlay: An Agent Framework for Language Learning Games
    by Bailis et al., NeurIPS GAIED Workshop 2023.
  14. Evaluating ChatGPT and GPT-4 for Visual Programming
    by Singla et al., ICER Poster 2023.
  15. Neural Task Synthesis for Visual Programming
    by Pădurean et al., TMLR 2024.
  16. Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming
    by Pădurean et al., Preprint 2024.
  17. Large Language Models for In-Context Student Modeling: Synthesizing Student's Behavior in Visual Programming
    by Nguyen et al., EDM 2024.
  18. GPTeach: Interactive TA Training with GPT-based Students
    by Markel et al., L@S 2023.
  19. Ruffle&Riley: Towards the Automated Induction of Conversational Tutoring Systems
    by Schmucker et al., NeurIPS GAIED Workshop 2023.
  20. Generative Agent for Teacher Training: Designing Educational Problem-Solving Simulations with Large Language Model-based Agents for Pre-Service Teachers
    by Lee et al., NeurIPS GAIED Workshop 2023.

Organizers

  • Adish Singla. Max Planck Institute for Software Systems (Saarbrucken, Germany).