The Application of a Large Language Model (LLM) in Education Reform and Innovation

A special issue of Systems (ISSN 2079-8954). This special issue belongs to the section "Artificial Intelligence and Digital Systems Engineering".

Deadline for manuscript submissions: 15 November 2025 | Viewed by 3676

Special Issue Editors


E-Mail Website
Guest Editor
School of International Studies, Communication University of China, Beijing 100024, China
Interests: AI teaching system; education reform

Special Issue Information

Dear Colleagues,

A large language model (LLM) is a system that belongs to generative artificial intelligence technology represented by ChatGPT. It involves important content such as curriculum design, data-driven teaching decision making, teaching evaluation, teaching application, teaching optimization, curriculum teaching platform, talent cultivation, teaching innovation, etc. It requires continuous reform and innovation to improve the system and its quality. The application of an LLM is conducive to promoting scientific decision making of curriculum design and teaching management. Decision making, as a key link and important function of an LLM in education innovation, is directly related to normal operation and teachers’ effectiveness in using data tools, as well as regarding technological developments concerning scientific proof and quality. In an LLM supported by big data and artificial intelligence, there are a number of scientific research studies on curriculum design, teaching decision making and evaluation. By analyzing and processing these data, it can be transformed into important educational information. Ultimately, it can be integrated into the decision-making process in teaching management, which is conducive to providing a scientific basis and reference for education innovation and formulating strategies.

The following topics are welcome:

  • Reform of professional curriculum design in the perspective of a large language model (LLM);
  • Construction of teaching decision making from the perspective of a large language model (LLM);
  • Intelligent evaluation of teaching decision making from the perspective of a large language model (LLM);
  • Personalized learning strategies from the perspective of a large language model (LLM);
  • Teaching assistance strategies from the perspective of a large language model (LLM);
  • Language writing strategies from the perspective of a large language model (LLM);
  • Optimization approaches for curriculum teaching system from the perspective of a large language model (LLM);
  • Improving teaching management in light of big data analysis and LLMs;
  • Application of teaching platform supported by a large language model (LLM);
  • Ethical challenges of LLM applications.

Dr. Feng Zhang
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Systems is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • large language model application
  • big data
  • education innovation

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (4 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

19 pages, 2493 KB  
Article
Harnessing Generative Artificial Intelligence to Construct Multimodal Resources for Chinese Character Learning
by Jinglei Yu, Jiachen Song and Yu Lu
Systems 2025, 13(8), 692; https://doi.org/10.3390/systems13080692 - 13 Aug 2025
Viewed by 331
Abstract
In Chinese character learning, distinguishing similar characters is challenging for learners regardless of their proficiency. This is due to the complex orthography (visual word form) linking symbol, pronunciation, and meaning. Multimedia learning is a promising approach to implement learning strategies for Chinese characters. [...] Read more.
In Chinese character learning, distinguishing similar characters is challenging for learners regardless of their proficiency. This is due to the complex orthography (visual word form) linking symbol, pronunciation, and meaning. Multimedia learning is a promising approach to implement learning strategies for Chinese characters. However, the availability of multimodal resources specifically designed for distinguishing similar Chinese characters is limited. With the advanced development of generative artificial intelligence (GenAI), we propose a practical framework for constructing multimodal resources, enabling flexible and semi-automated resource generation for Chinese character learning. The framework first constructs image illustrations due to their broad applicability across various learning contexts. After that, other four types of multimodal resources implementing learning strategies for similar character learning can be developed in the future, including summary slide, micro-video, self-test question, and basic information. An experiment was conducted with one group receiving the constructed multimodal resources and the other receiving the traditional text-based resources for similar character learning. We explored the participants’ learning performance, motivation, satisfaction, and attitudes. The results showed that the multimodal resources significantly improved performance on distinguishing simple characters, but were not suitable for non-homophones, i.e., visually similar characters with different pronunciations. Micro-videos introducing character formation knowledge significantly increased students’ learning motivation for character evolution and calligraphy. Overall, the resources received high satisfaction, especially for micro-videos and image illustrations. The findings regarding the effective design of multimodal resources for implementing learning strategies (e.g., using visual mnemonics, character formation knowledge, and group reviews) and implications for different Chinese character types are also discussed. Full article
Show Figures

Figure 1

19 pages, 2135 KB  
Article
Development of an Automotive Electronics Internship Assistance System Using a Fine-Tuned Llama 3 Large Language Model
by Ying-Chia Huang, Hsin-Jung Tsai, Hui-Ting Liang, Bo-Siang Chen, Tzu-Hsin Chu, Wei-Sho Ho, Wei-Lun Huang and Ying-Ju Tseng
Systems 2025, 13(8), 668; https://doi.org/10.3390/systems13080668 - 6 Aug 2025
Viewed by 492
Abstract
This study develops and validates an artificial intelligence (AI)-assisted internship learning platform for automotive electronics based on the Llama 3 large language model, aiming to enhance pedagogical effectiveness within vocational training contexts. Addressing critical issues such as the persistent theory–practice gap and limited [...] Read more.
This study develops and validates an artificial intelligence (AI)-assisted internship learning platform for automotive electronics based on the Llama 3 large language model, aiming to enhance pedagogical effectiveness within vocational training contexts. Addressing critical issues such as the persistent theory–practice gap and limited innovation capability prevalent in existing curricula, we leverage the natural language processing (NLP) capabilities of Llama 3 through fine-tuning based on transfer learning to establish a specialized knowledge base encompassing fundamental circuit principles and fault diagnosis protocols. The implementation employs the Hugging Face Transformers library with optimized hyperparameters, including a learning rate of 5 × 10−5 across five training epochs. Post-training evaluations revealed an accuracy of 89.7% on validation tasks (representing a 12.4% improvement over the baseline model), a semantic comprehension precision of 92.3% in technical question-and-answer assessments, a mathematical computation accuracy of 78.4% (highlighting this as a current limitation), and a latency of 6.3 s under peak operational workloads (indicating a system bottleneck). Although direct trials involving students were deliberately avoided, the platform’s technical feasibility was validated through multidimensional benchmarking against established models (BERT-base and GPT-2), confirming superior domain adaptability (F1 = 0.87) and enhanced error tolerance (σ2 = 1.2). Notable limitations emerged in numerical reasoning tasks (Cohen’s d = 1.15 compared to human experts) and in real-time responsiveness deterioration when exceeding 50 concurrent users. The study concludes that Llama 3 demonstrates considerable promise for automotive electronics skills development. Proposed future enhancements include integrating symbolic AI modules to improve computational reliability, implementing Kubernetes-based load balancing to ensure latency below 2 s at scale, and conducting longitudinal pedagogical validation studies with trainees. This research provides a robust technical foundation for AI-driven vocational education, especially suited to mechatronics fields that require close integration between theoretical knowledge and practical troubleshooting skills. Full article
Show Figures

Figure 1

18 pages, 1222 KB  
Article
Enhancing Programming Performance, Learning Interest, and Self-Efficacy: The Role of Large Language Models in Middle School Education
by Bixia Tang, Jiarong Liang, Wenshuang Hu and Heng Luo
Systems 2025, 13(7), 555; https://doi.org/10.3390/systems13070555 - 8 Jul 2025
Viewed by 596
Abstract
Programming education has become increasingly vital within global K–12 curricula, and large language models (LLMs) offer promising solutions to systemic challenges such as limited teacher expertise and insufficient personalized support. Adopting a human-centric and systems-oriented perspective, this study employed a six-week quasi-experimental design [...] Read more.
Programming education has become increasingly vital within global K–12 curricula, and large language models (LLMs) offer promising solutions to systemic challenges such as limited teacher expertise and insufficient personalized support. Adopting a human-centric and systems-oriented perspective, this study employed a six-week quasi-experimental design involving 103 Grade 7 students in China to investigate the effects of instruction supported by the iFLYTEK Spark model. Results showed that the experimental group significantly outperformed the control group in programming performance, cognitive interest, and programming self-efficacy. Beyond these quantitative outcomes, qualitative interviews revealed that LLM-assisted instruction enhanced students’ self-directed learning, a sense of real-time human–machine interaction, and exploratory learning behaviors, forming an intelligent human–AI learning system. These findings underscore the integrative potential of LLMs to support competence, autonomy, and engagement within digital learning systems. This study concludes by discussing the implications for intelligent educational system design and directions for future socio-technical research. Full article
Show Figures

Figure 1

22 pages, 706 KB  
Article
Privacy Ethics Alignment in AI: A Stakeholder-Centric Framework for Ethical AI
by Ankur Barthwal, Molly Campbell and Ajay Kumar Shrestha
Systems 2025, 13(6), 455; https://doi.org/10.3390/systems13060455 - 9 Jun 2025
Cited by 1 | Viewed by 998
Abstract
The increasing integration of artificial intelligence (AI) in digital ecosystems has reshaped privacy dynamics, particularly for young digital citizens navigating data-driven environments. This study explores evolving privacy concerns across three key stakeholder groups—young digital citizens, parents/educators, and AI professionals—and assesses differences in data [...] Read more.
The increasing integration of artificial intelligence (AI) in digital ecosystems has reshaped privacy dynamics, particularly for young digital citizens navigating data-driven environments. This study explores evolving privacy concerns across three key stakeholder groups—young digital citizens, parents/educators, and AI professionals—and assesses differences in data ownership, trust, transparency, parental mediation, education, and risk–benefit perceptions. Employing a grounded theory methodology, this research synthesizes insights from key participants through structured surveys, qualitative interviews, and focus groups to identify distinct privacy expectations. Young digital citizens emphasized autonomy and digital agency, while parents and educators prioritized oversight and AI literacy. AI professionals focused on balancing ethical design with system performance. The analysis revealed significant gaps in transparency and digital literacy, underscoring the need for inclusive, stakeholder-driven privacy frameworks. Drawing on comparative thematic analysis, this study introduces the Privacy–Ethics Alignment in AI (PEA-AI) model, which conceptualizes privacy decision-making as a dynamic negotiation among stakeholders. By aligning empirical findings with governance implications, this research provides a scalable foundation for adaptive, youth-centered AI privacy governance. Full article
Show Figures

Figure 1

Back to TopTop