An Interaction Design for Machine Teaching to Develop AI Tutors
Authors
Intelligent tutoring systems (ITSs) have consistently been shown to improve the educational outcomes of students when used alone or combined with traditional instruction. However, building an ITS is a time-consuming process which requires specialized knowledge of existing tools. Extant authoring methods, including the Cognitive Tutor Authoring Tools' (CTAT) example-tracing method and SimStudent's Authoring by Tutoring, use programming-by-demonstration to allow authors to build ITSs more quickly than they could by hand programming with model-tracing. Yet these methods still suffer from long authoring times or difficulty creating complete models. In this study, we demonstrate that Simulated Learners built with the Apprentice Learner (AL) Framework can be combined with a novel interaction design that emphasizes model transparency, input flexibility, and problem solving control to enable authors to achieve greater model completeness in less time than existing authoring methods.
Research Questions / Practical Problems
Question signals indexed for this paper.
- 80%
Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation
CHI '25· Human-LLM Collaboration +1
- 80%
Good Fences Make Good Learning: How Self-Directed Language Learners Navigate LLM Delegation Decisions
CHI '26· Human-LLM Collaboration +1
- 80%
AskNow: An LLM-powered Interactive System for Real-Time Question Answering in Large-Scale Classrooms
CHI '26· Human-LLM Collaboration +1
- 80%
AI meets Mathematics Education: Supporting Instructors in Large Mathematics Classes with Context-Aware AI
CHI '26· Human-LLM Collaboration +1
- 80%
Can an AI Partner Empower Learners to Ask Critical Questions?
IUI '25· Human-LLM Collaboration +1
- 67%
Charting the Future of AI in Project-Based Learning: A Co-Design Exploration with Students
CHI '24· Human-LLM Collaboration +1
- 67%
Unlocking Scientific Concepts: How Effective Are LLM-Generated Analogies for Student Understanding and Classroom Practice?
CHI '25· Human-LLM Collaboration +1
- 67%
Supporting Learners' Use of Imperfect Generative Pedagogical Chatbots: The Role of Chatbot Response Uncertainty and Reduced Verbosity
CHI '26· Conversational Chatbots +2
- 67%
An Empirical Study to Understand How Students Use ChatGPT for Writing Essays
CHI '26· Human-LLM Collaboration +2
- 67%
Who You Explain To Matters: Learning by Explaining to Conversational Agents with Different Pedagogical Roles
CHI '26· Intelligent Tutoring Systems & Learning Analytics +2
Based on Jaccard similarity of research subtopics & professions (≥60%)