Date
Publisher
arXiv
Project-based learning (PBL) is an instructional method that is very helpful
in nurturing students' creativity, but it requires significant time and energy
from both students and teachers. Large language models (LLMs) have been proven
to assist in creative tasks, yet much controversy exists regarding their role
in fostering creativity. This paper explores the potential of LLMs in PBL
settings, with a special focus on fostering creativity. We began with an
exploratory study involving 12 middle school students and identified five
design considerations for LLM applications in PBL. Building on this, we
developed an LLM-empowered, 48-hour PBL program and conducted an instructional
experiment with 31 middle school students. Our results indicated that LLMs can
enhance every stage of PBL. Additionally, we also discovered ambivalent
perspectives among students and mentors toward LLM usage. Furthermore, we
explored the challenge and design implications of integrating LLMs into PBL and
reflected on the program. By bridging AI advancements into educational
practice, our work aims to inspire further discourse and investigation into
harnessing AI's potential in child-centric educational settings.
Study at a glance
- Question: How can large language models support students' creative project-based learning, and what challenges arise?
- Setting and data: Urban middle school in China, 31 students aged 15-16 across seven groups, guided by seven college mentors during a 48-hour program.
- Method: Instructional experiment using structured observations and post-program semi-structured interviews analyzed with inductive thematic analysis.
Why it matters
Project-based learning fosters student creativity but demands extensive time and energy. Although large language models can assist with creative tasks, their actual use in project-based classrooms remains rare and controversial.
Key findings
- Large language models supported every project-based learning stage by helping students discover structured domain knowledge, define real problems, brainstorm solutions, and deliver prototypes.
- Students displayed conflicted attitudes toward AI tools, with some reporting expanded thinking while others feared generated ideas would restrict creativity or reduce deep understanding.
- Groups faced practical challenges including difficulties formulating effective prompts, unequal device access among members, and heavy reliance on mentors for guidance.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who age?
Why use AI?
Study design
