Application of Large Language Models to Enhance Student Support Services in the Context of University Autonomy
DOI:
https://doi.org/10.46328/ijres.5312Keywords:
Higher education, Large language models, Learner support, Personalized learning, University autonomyAbstract
This systematic review analyzes research on the application of Large Language Models (LLMs) to enhance the quality of learner support in the context of university autonomy. The study aims to evaluate the current applications of LLMs in providing personalized and adaptive learning paths, identify ethical challenges, and analyze the role of prompt engineering and human-in-the-loop supervision. The research method involves a systematic analysis of scientific works published up to mid-2024. The findings indicate that LLMs significantly enhance personalized feedback and adaptive tutoring, thereby promoting self-regulated learning and student engagement. However, challenges related to feedback accuracy and ethical issues persist, requiring robust governance frameworks. The conclusion emphasizes that effective LLM integration requires combining technological power with pedagogical expertise and human oversight to optimize the educational experience and successfully support autonomous learners.
References
Alhafni, B., Vajjala, S., Banno, S., Maurya, K. K., & Kochmar, E. (2024). Llms in education: Novel perspectives, challenges, and opportunities. arXiv. https://doi.org/10.48550/arxiv.2409.11917
AlSobeh, A. M. R., & Woodward, B. (2023). Al as a partner in learning: A novel student-in-the-loop framework for enhanced student engagement and outcomes in higher education. Proceedings of the 16th International Conference on PErvasive Technologies Related to Assistive Environments. https://doi.org/10.1145/3585059.3611405
Andonov, V. (2024). Enhancing university students' activities with interactive immediate feedback using customized llms. 2024 16th International Conference on Computer Science and Information Technologies (CSIT). https://doi.org/10.1109/comsci63166.2024.10778529
Bewersdorff, A., Hartmann, C., Hornberger, M., Sessler, K., Bannert, M., Kasneci, E., Kasneci, G., Zhai, X., & Nerdel, C. (2024). Taking the next step with generative artificial intelligence: The transformative role of multimodal large language models in science education. arXiv. https://doi.org/10.48550/arxiv.2401.00832
Chen, Y., Ding, N., Zheng, H., Liu, Z., Sun, M., & Zhou, B. (2023). Empowering private tutoring by chaining large language models. arXiv. https://doi.org/10.48550/arxiv.2309.08112
Choi, H., & Abdirayimov, S. (2024). Revolutionizing education: The era of large language models. Journal of Multimedia Information System, 11(1), 97-106. https://doi.org/10.33851/jmis.2024.11.1.97
Daheim, N., Mačina, J., Kapur, M., Gurevych, I., & Sachan, M. (2024). Stepwise verification and remediation of student reasoning errors with large language model tutors. arXiv. https://doi.org/10.48550/arxiv.2407.09136
Dai, W., Lin, J., Jin, H., Li, T., Tsai, Y., Gašević, D., & Chen, G. (2023). Can large language models provide feedback to students? A case study on chatgpt. 2023 IEEE 23rd International Conference on Advanced Learning Technologies (ICALT). https://doi.org/10.1109/icalt58122.2023.00100
Dakshit, S. (2024). Faculty perspectives on the potential of rag in computer science higher education. arXiv. https://doi.org/10.48550/arxiv.2408.01462
Dong, B., Bai, J., Xu, T., & Zhou, Y. (2024). Large language models in education: A systematic review. 2024 9th International Conference on Computer and Communication Systems (ICCCS). https://doi.org/10.1109/cste62025.2024.00031
Eager, B. (2023). Prompting higher education towards ai-augmented teaching and learning practice. Journal of University Teaching and Learning Practice, 20(5). https://doi.org/10.53761/1.20.5.02
Gan, W., Qi, Z., Wu, J., & Lin, C. (2023). Large language models in education: Vision and opportunities. arXiv. https://doi.org/10.48550/arxiv.2311.13160
Jacobs, S., & Jaschke, S. (2024). Evaluating the application of large language models to generate feedback in programming education. arXiv. https://doi.org/10.48550/arxiv.2403.09744
Jacobsen, L. J., Rohlmann, J., & Weber, K. E. (2025). Al feedback in education: The impact of prompt design and human expertise on Ilm performance. https://doi.org/10.31219/osf.io/fx5qz
Kiesler, N., Lohr, D., & Keuning, H. (2023). Exploring the potential of large language models to generate formative programming feedback. arXiv. https://doi.org/10.48550/arxiv.2309.00029
Kumar, H., Musabirov, I., Reza, M., Shi, J., Wang, X. D., Williams, J. J., Kuzminykh, A., & Liut, M. (2024). Guiding students in using Ilms in supported learning environments: Effects on interaction dynamics, learner performance, confidence, and trust. Proceedings of the ACM on Human-Computer Interaction, 8(CSCW2), 1-30. https://doi.org/10.1145/3687038
Li, Q., Xie, Y., Chakravarty, S., & Lee, D. (2024). Edumas: A novel Ilm-powered multi-agent framework for educational support. 2024 IEEE International Conference on Big Data (BigData). https://doi.org/10.1109/bigdata62323.2024.10826103
Meyer, J., Jansen, T., Schiller, R., Liebenow, L., Steinbach, M., Horbach, A., & Fleckenstein, J. (2023). Using Ilms to bring evidence-based feedback into the classroom: Ai-generated feedback increases secondary students' text revision, motivation, and positive emotions. Computers and Education: Artificial Intelligence. https://doi.org/10.1016/j.caeai.2023.100199
Modran, H. A., Bogdan, C., Ursuțiu, D., Samoilă, C., & Modran, P. L. (2024). Llm intelligent agent tutoring in higher education courses using a rag approach. Preprints. https://doi.org/10.20944/preprints202407.0519.v1
Moore, W., & Tsay, L. (2024). From data to decisions: Leveraging Al for proactive education strategies. Proceedings of the International Conference on Al Research, 4(1), 281-288. https://doi.org/10.34190/icair.4.1.3082
Ng, C., & Fung, Y. (2024). Educational personalized learning path planning with large language models. arXiv. https://doi.org/10.48550/arxiv.2407.11773
Nikolopoulou, K. (2024). Generative artificial intelligence in higher education: Exploring ways of harnessing pedagogical practices with the assistance of chatgpt. BONVIEW International Journal of Continuing Education, 4(2), 24-89. https://doi.org/10.47852/bonviewijce42022489
Poličar, P. G., Špendl, M., Curk, T., & Zupan, B. (2025). Automated assignment grading with large language models: Insights from a bioinformatics course. arXiv. https://doi.org/10.48550/arxiv.2501.14499
Pozdniakov, S., Brazil, J., Abdi, S., Bakharia, A., Sadiq, S., Gašević, D., Denny, P., & Khosravi, H. (2024). Large language models meet user interfaces: The case of provisioning feedback. arXiv. https://doi.org/10.48550/arxiv.2404.11072
Raihan, N., Siddiq, M. L., Santos, J. C. S., & Zampieri, M. (2024). Large language models in computer science education: A systematic literature review. arXiv. https://doi.org/10.48550/arxiv.2410.16349
Schultze, T., Kumar, V., McKeown, G., O'Connor, P., Rychlowska, M., & Sparemblek, K. (2024). Using large language models to augment (rather than replace) human feedback in higher education improves perceived feedback quality. PsyArXiv. https://doi.org/10.31234/osf.io/tvcag
Shahzad, T., Mazhar, T., Tariq, M. U., Ahmad, W., Ouahada, K., & Hamam, H. (2025). A comprehensive review of large language models: Issues and solutions in learning environments. Discover Sustainability, 6(1). https://doi.org/10.1007/s43621-025-00815-8
Shen, S. (2024). Application of large language models in the field of education. Theoretical and Natural Science, 34(1), 140-147. https://doi.org/10.54254/2753-8818/34/20241163
Steinert, S., Avila, K. E., Ruzika, S., Kühn, J., & Küchemann, S. (2023). Harnessing large language models to enhance self-regulated learning via formative feedback. arXiv. https://doi.org/10.48550/arxiv.2311.13984
Steinert, S., Avila, K. E., Ruzika, S., Kühn, J., & Küchemann, S. (2024). Harnessing large language models to develop research-based learning assistants for formative feedback. Smart Learning Environments, 11(1). https://doi.org/10.1186/s40561-024-00354-1
Wang, S., Xu, T., Li, H., Zhang, C., Liang, J., Tang, J., Yu, P. S., & Wen, Q. (2024). Large language models for education: A survey and outlook. arXiv. https://doi.org/10.48550/arxiv.2403.18105
Wen, Q., Liang, J., Sierra, C., Luckin, R., Tong, R., Liu, Z., Cui, P., & Tang, J. (2024). Al for education (ai4edu): Advancing personalized education with Ilm and adaptive learning. Proceedings of the ACM on Web Conference 2024. https://doi.org/10.1145/3637528.3671498
Yu, J., Zhang, Z., Zhang-Li, D., Tu, S., Hao, Z., Li, R., Li, H., Wang, Y. F., Li, H., Gong, L., Cao, J., Lin, J., Zhou, J., Qin, F., Wang, H., Jiang, J., Deng, L., Zhan, Y. H., Xiao, C., ... Sun, M. (2024). From mooc to maic: Reshaping online teaching and learning through Ilm-driven agents. arXiv. https://doi.org/10.48550/arxiv.2409.03512
Zhang, X., Zhang, X., & Liu, H. (2024). Reflections on enhancing higher education classroom effectiveness through the introduction of large language models. Journal of Modern Educational Research, 3, 19-19. https://doi.org/10.53964/jmer.2024019
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Research in Education and Science
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Articles may be used for research, teaching, and private study purposes. Authors alone are responsible for the contents of their articles. The journal owns the copyright of the articles. The publisher shall not be liable for any loss, actions, claims, proceedings, demand, or costs or damages whatsoever or howsoever caused arising directly or indirectly in connection with or arising out of the use of the research material.
The author(s) of a manuscript agree that if the manuscript is accepted for publication in the International Journal of Research in Education and Science (IJRES), the published article will be copyrighted using a Creative Commons “Attribution 4.0 International” license. This license allows others to freely copy, distribute, and display the copyrighted work, and derivative works based upon it, under certain specified conditions.
Authors are responsible for obtaining written permission to include any images or artwork for which they do not hold copyright in their articles, or to adapt any such images or artwork for inclusion in their articles. The copyright holder must be made explicitly aware that the image(s) or artwork will be made freely available online as part of the article under a Creative Commons “Attribution 4.0 International” license.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
