Based on Large Language Models’ Cross-disciplinary Project Design
Download PDF
$currentUrl="http://$_SERVER[HTTP_HOST]$_SERVER[REQUEST_URI]"

Keywords

LLM
Self-regulated learning
Higher-order thinking skills
Knowledge construction

DOI

10.26689/erd.v7i7.11500

Submitted : 2025-07-06
Accepted : 2025-07-21
Published : 2025-08-05

Abstract

The deep integration of large language models (LLMs) with education and teaching is redefining the connotations of knowledge acquisition, learning processes, and human-machine collaborative teaching, heralding a new era of “hybrid” educational destiny communities. As a breakthrough technology in the AI era, LLMs bring enormous opportunities and challenges to technology-enabled education. Against this backdrop, this article analyzes the value of applying LLMs in basic education for students’ self-regulated learning, higher-order thinking skills, and knowledge construction. Combining these values, the article proposes a targeted implementation path for designing cross-disciplinary projects using LLMs, delving into the three stages of “foreseeing, performing, and self-reflecting,” and analyzing them with specific case studies to promote the deep integration of LLMs and education.

References

Chu L, Wang H, Chen X, 2024, Adolescent Education on Large Language Models for Large Language Models. China Educational Technology, 2024(4): 32–44.

Guo N, Dong Q, Xu X, et al., 2023, Preliminary Exploration of Teaching Methods for Data Structure Course Based on Chat GPT. Science, Education and Culture Journal, 2023(21): 95–100.

Liang Y, Pu J, Yuan S, 2023, “AI + Primary School Science” Interdisciplinary Teaching Under the Guidance of Big Concepts – A Case Study of “Exploring the Mystery of the Alternation of Seasons”. Modern Educational Technology, 33(11): 57–68.

Wei J, Zhang Q, 2024, Project-Based Learning in Primary School Mathematics: Development, Design, and Reflection – A Case Study of “Mathematical Problems in Average Pace”. Journal of Mathematics Education, 33(3): 52–56.

Xu J, Yan R, 2024, On the Evidentiary Attribute of Large Language Model Materials – Taking ChatGPT and Chat GPT as Examples. Journal of Sichuan Normal University (Social Sciences Edition), 51(1): 60–73 + 202–203.

Lin C, 2017, A Study on Chinese Students’ Core Competencies. Studies of Psychology and Behavior, 15(2): 145–154.

Dai Y, Liu A, Lim C, 2023, Reconceptualizing ChatGPT and Generative AI as a Student-Driven Innovation in Higher Education. Procedia CIRP, 119: 84–90.

Han Y, Zhao X, Shen S, 2024, Human–Machine Collaborative Regulation: A New Path for Self-Regulated Learning from the Perspective of Composite Brain. E-Education Research, 45(5): 20–26 + 34.

Somasundaram M, Junaid K, Mangadu S, 2020, Artificial Intelligence (AI) Enabled Intelligent Quality Management System (IQMS) for Personalized Learning Path. Procedia Computer Science, 172: 438–442.

Zimmerman B, 1989, A Social Cognitive View of Self-Regulated Academic Learning. Journal of Educational Psychology, 81(3): 329–339.

Chai S, 2017, Knowledge Construction Leads Educational Innovation: Theory, Practice and Challenges: An Interview with International Renowned Learning Sciences Experts Professor Brett and Professor Scardamalia. Open Education Research, 23(4): 4–11.

Wu C, Zhang M, 2010, Connotation, Examples and Essential Characteristics of American Biology “5E” Teaching Model. Curriculum, Teaching Material and Method, 30(6): 108–112.

Zimmerman B, 2002, Becoming a Self-Regulated Learner: An Overview. Theory into Practice, 41(2): 64–70.

Cooper G, 2023, Examining Science Education in ChatGPT: An Exploratory Study of Generative Artificial Intelligence. Journal of Science Education and Technology, 32(3): 444–452.

Kuo Y, Tuan H, Chin C, 2020, The Influence of Inquiry-Based Teaching on Male and Female Students’ Motivation and Engagement. Research in Science Education, 50(2): 549–572.