Designing Child-Centric AI Learning Environments: Insights from LLM-Enhanced Creative Project-Based Learning
Project Overview
The document explores the integration of Large Language Models (LLMs) in Project-Based Learning (PBL) environments, emphasizing their potential to enhance creativity and problem-solving skills among middle school students. An exploratory study identified key design considerations for effectively implementing LLM applications in PBL, followed by an instructional experiment that demonstrated the supportive role of LLMs across various stages of the learning process. The findings highlight significant benefits, such as increased student creativity and engagement, while also addressing challenges that arise during implementation, including the necessity for mentor training and the establishment of structured usage protocols to optimize LLM effectiveness. Overall, the document underscores the transformative potential of generative AI in educational settings, particularly in fostering innovative learning experiences through tailored support in PBL frameworks.
Key Applications
LLM-empowered Project-Based Learning Program
Context: Middle school students participating in a 48-hour PBL program focused on creating a low-carbon campus.
Implementation: An instructional experiment designed based on design considerations identified in exploratory studies, involving structured PBL stages and LLM tools.
Outcomes: Enhanced creativity, improved problem-solving skills, and effective support in all stages of PBL.
Challenges: Struggles in formulating effective prompts, overreliance on mentors, and balancing LLM use with group collaboration.
Implementation Barriers
Technical Barrier
Students struggle to formulate effective questions for LLMs due to their unfamiliarity with prompting techniques, leading to excessive reliance on mentors for guidance.
Proposed Solutions: Provide training on formulating effective queries, examples of successful LLM interactions, and implement clear mentor roles to facilitate student autonomy in using LLMs.
Collaboration Barrier
Challenges in defining the role of LLMs in collaborative settings, leading some students to dominate LLM interactions while others disengage.
Proposed Solutions: Establish protocols for equitable LLM access among group members and promote joint usage.
Project Team
Siyu Zha
Researcher
Yuehan Qiao
Researcher
Qingyu Hu
Researcher
Zhongsheng Li
Researcher
Jiangtao Gong
Researcher
Yingqing Xu
Researcher
Contact Information
For information about the paper, please contact the authors.
Authors: Siyu Zha, Yuehan Qiao, Qingyu Hu, Zhongsheng Li, Jiangtao Gong, Yingqing Xu
Source Publication: View Original PaperLink opens in a new window
Project Contact: Dr. Jianhua Yang
LLM Model Version: gpt-4o-mini-2024-07-18
Analysis Provider: Openai