Date
AI Overview
Why it matters
Students often use generative AI to bypass learning processes by seeking direct answers, missing essential cognitive steps and creating disparities in educational outcomes.
Study at a glance
- Question: How can instructors design an AI tool to guide student learning in statistics homework without giving away direct answers?
- Setting and data: Simulated undergraduate Statistical Computing course in R, designed by the authors.
- Method: System development and design illustration using simulated case studies.
- AI tools: LLteacher, GPT-5
Key findings
- LLteacher uses a two-layer prompt system to guide students through conversational problem-solving while preventing the AI model from revealing direct solutions.
- The tool supports both the recall of prior knowledge and the discovery of unintroduced statistical concepts through error-driven, adaptive feedback.
- Logging full student-AI conversation histories allows instructors to maintain transparency, review learning processes, and identify attempts to circumvent guided inquiry.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
As generative AI becomes increasingly embedded in everyday life, the thoughtful and intentional integration of AI-based tools into statistics education has become essential. We address this need with a focus on homework assignments and we propose the use of LLMs as a companion to complete homework by developing an open-source tool named LLteacher. This LLM-based tool preserves learning processes and it guides students to engage with AI in ways that support their learning, while ensuring alignment with course content and equitable access. We illustrate LLteacher's design and functionality with examples from an undergraduate Statistical Computing course in R, showing how it supports two distinct pedagogical goals: recalling prior knowledge and discovering new concepts. While this is an initial version, LLteacher demonstrates one possible pathway for integrating generative AI into statistics courses, with strong potential for adaptation to other types of classes and assignments.
Research Categories
What is the application?
Who age?
Methods
Publication Source
Publisher
arXiv
