Research ArticleOpen AccessGoogle Scholar indexed
The Advantages and Constraints of LLM-Augmented Knowledge Graphs in University Innovation and Entrepreneurship Education
School of Electronic Information Engineering, Inner Mongolia University, Hohhot, China
School of Electronic Information Engineering, Inner Mongolia University, Hohhot, China
School of Electronic Information Engineering, Inner Mongolia University, Hohhot, China
- 1 School of Electronic Information Engineering, Inner Mongolia University, Hohhot, China
- 2 School of Electronic Information Engineering, Inner Mongolia University, Hohhot, China
- 3 School of Electronic Information Engineering, Inner Mongolia University, Hohhot, China
Advances in Applied Sociology·Volume 16 (2026)·Pages 38–47·Published 6 January 2026·DOI10.4236/aasoci.2026.161003
Copy link · social · email
Abstract
This paper investigates the integration of Large Language Models with Knowledge Graphs (LLM-KGs) into the pedagogical framework of higher education, specifically within innovation and entrepreneurship programs. It argues that this synergy can catalyze a shift toward more intelligent and data-informed educational practices. However, the implementation is scrutinized through a critical lens, revealing significant constraints in data governance, a growing digital divide among faculty, and systemic institutional inertia. In response, the study proposes a set of strategic interventions designed to provide both a conceptual foundation and actionable guidance for the effective adoption of LLM-KG systems in university settings.
KeywordsLarge-Scale ModelsKnowledge GraphInnovation and Entrepreneurship EducationConstraints
- Bai, Y., Jones, A., Ndousse, K. et al. (2022). Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback .
- Hadi, M. U., Qureshi, R., Shah, A. et al. (2023). A Survey on Large Language Models: Ap-plications, Challenges, Limitations, and Practical Usage .
- Hu, M. (2024). Research and Implementation of an Emotional Dialogue System Based on Reinforcement Learning from Human Feedback . Master’s Thesis, Zhongnan University of Economics and Law.
- Kaddour, J., Harris, J., Mozes, M. et al. (2024). Challenges and Applications of Large Language Models. IEEE Access, 12, 26839-26874.
- Li, X. (2005). A Review of Domestic Research on Lotka’s Law in Recent Years. Sci-Tech In-formation Development & Economy, No. 13, 27-28.
- Li, Y., Zhang, H., Wang, M. et al. (2024). Research on the Innovation and Entrepreneurship Education Model of New Agricultural Sciences Empowered by Artificial Intelligence. University, No. 17 , 146.
- Liu, B., & Dai, Z. (2025). Governance of the Digital Divide in Education: Realistic Landscape, Generation Mechanism, and Practical Approach. China Educational Technology, No. 1, 72-81.
- Liu, Z. (2021). Research on University Data Security Management under the Background of Smart Campus Construction. Network Security Technology & Application, No. 1, 102-103.
- Luo, J., & Zhang, Y. (2023). Evolution and Educational Application of Subject Knowledge Graphs Driven by Multimodal Large Models. Modern Educational Technology, 33, 76-88.
- Mi, Y., Xu, Z., & Luo, J. (2018). Exploration of Whole-Process Multi-Dimensional Collaborative Practical Education for Innovation and Entrepreneurship among College Students. Research and Exploration in Laboratory, 37, 237.
- Wang, X., Jin, P., Chen, Y. et al. (2021). Research on Data Security Risk Analysis and Countermeasures in University Data Centers. Journal of Beijing Union University, 35, 53-59.
- Wang, Z., & Shen, L. (2021). Review and Prospect of Innovation and Entrepreneurship Education Research in China: A Knowledge Graph Analysis Based on CiteSpace. Scientific Management Research, 39, 8.
- Wang, Z., & Shen, L. (2025). Research on the Collaborative Education Practice Path of University Ideological and Political Courses and Curriculum Ideology and Politics Based on Knowledge Graphs. Journal of Social Science of Jiamusi University, 43, 172.