The DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.
The role of large language models in personalized learning: a systematic review of educational impact
Open accessAbstract
The rapid evolution of technology has significantly transformed the educational landscape, with the advent of Large Language Models (LLMs) introducing new possibilities for personalized learning. This systematic review examines the educational impact of LLM-based learning systems compared to traditional educational approaches, focusing on six critical research questions. These questions explore the effectiveness of LLMs in enhancing student engagement, emotional and social development, real-time progress monitoring, and their role in creating fair and rigorous examination environments. Furthermore, the review addresses challenges such as ethical considerations, privacy concerns, and the extent to which LLMs can simulate real-world teaching experiences. A total of 55 studies, published between 2020 and 2024, were systematically analyzed to explore the impact of Large Language Models (LLMs) on educational outcomes, including emotional, social, and academic development. These studies included a combination of peer-reviewed articles, conference papers, and journal publications, which were selected through a set of predetermined inclusion and exclusion criteria. Quality assessment criteria ensured the inclusion of high-quality research focusing on the application of LLM-based AI technology in education. The review also highlights key challenges and limitations, including issues of accessibility, ethical dilemmas, and the integration of AI into traditional education systems. Findings underscore the potential of LLMs to revolutionize education through personalized learning, while also addressing the critical need for rigorous evaluation and ethical deployment to ensure equitable and effective outcomes.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
(1978) · Medical Entomology and Zoology · Cited by 53,488
Literature review as a research methodology: An overview and guidelines
Snyder, H. (2019) · Journal of Business Research · doi:10.1016/j.jbusres.2019.07.039 · Cited by 11,524
Durlak, J. A., Weissberg, R. P., Dymnicki, A. B., Taylor, R. D., & Schellinger, K. B. (2011) · Child Development · doi:10.1111/j.1467-8624.2010.01564.x · Cited by 10,854
Zawacki-Richter, O., Marín, V. I., Bond, M., & Gouverneur, F. (2019) · International Journal of Educational Technology in Higher Education · doi:10.1186/s41239-019-0171-0 · Cited by 7,242 · cited 1×
“According to Zawacki-Richter et al. [21], AI in education has been shown to significantly improve learning outcomes by providing tailored feedback and immediate support.”
Dwivedi, Y. K., Kshetri, N., Hughes, L., Slade, E. L., Jeyaraj, A., Kar, A. K., Baabdullah, A. M., Koohang, A., Raghavan, V., Ahuja, M., et al. (2023) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2023.102642 · Cited by 4,584
Visible learning: a synthesis of over 800 meta‐analyses relating to achievement
Carter, M. (2009) · Educational Psychology · doi:10.1080/01443410903415150 · Cited by 4,581
VanLEHN, K. (2011) · Educational Psychologist · doi:10.1080/00461520.2011.611369 · Cited by 2,323
Science of Education and the Psychology of the Child
Moore, G. T., & Piaget, J. (1971) · Journal of Architectural Education (1947-1974) · doi:10.2307/1423801 · Cited by 1,892
Evolution and Revolution in Artificial Intelligence in Education
Roll, I., & Wylie, R. (2016) · International Journal of Artificial Intelligence in Education · doi:10.1007/s40593-016-0110-3 · Cited by 1,229 · cited 1×
“Another study by Roll and Wylie [25] emphasized that AI-driven adaptive learning systems can improve conceptual understanding, particularly in subjects like math and science, where individualized pacing is critical.”
AI technologies for education: Recent research & future directions
Zhang, K., & Aslan, A. B. (2021) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2021.100025 · Cited by 923
Research works printed but not linked: 16
- Dimitriadou E, Lanitis A. A critical evaluation, challenges, and future perspectives of using artificial intelligence and emerging technologies in smart classrooms. Smart Learn Environ. 2023;10(12):1–24.
- Rachha A, Seyam M. Explainable AI in education: current trends, challenges, and opportunities. IEEE SoutheastCon. 2023;2023:232–9.
- Smith J, Johnson R, Lee T. AI in education: enhancing engagement and retention. J Educ Technol. 2023;45(3):215–30.
- Govaerts N, Kyndt E, Dochy F, Baert H. Influence of learning approach and context on workplace learning. J Work Learn. 2011;23(4):225–40.
- Holstein K, McLaren M, Aleven V. Student learning benefits of a mixed-reality teacher awareness tool in AI-enhanced classrooms. In Proceedings of the Tenth International Conference on Learning Analytics & Knowledge, 2020, pp. 544–553.
- Zohuri B, Mossavar-Rahmani F. Revolutionizing education: the dynamic synergy of personalized learning and artificial intelligence. Int J Adv Eng Manag Res. 2024;9(1):143–57.
- Doo MY, Bonk CJ, Heo H. A meta-analysis of scaffolding effects in online learning in higher education. Int Rev Res Open Distrib Learn. 2020;21(3):60–80.
- Chen H, Kumar P, Davis S. Emotional intelligence in education: the role of AI conversational systems. J Educ Psychol AI. 2023;12(4):45–67.
- Gonzalez L, Patel R. Enhancing social skills through AI-driven collaborative learning. Int J Educ Res. 2022;78(2):102–15.
- Rane NL, Choudhary SP, Rane J. Education 4.0 and 5.0: integrating artificial intelligence for personalized and adaptive learning. J Educ AI Integr. 2024;21(3):245–89.
- Ghimire A, Edwards J. Generative AI adoption in the classroom: TAM and IDT analysis. AI in Educ J. 2024;41(3):245–67.
- Mitra A. AgentInstruct: toward generative teaching with agentic flows. In: Proceedings of AI in Education, 2024, pp. 120–143.
- Liladhar NR. AI applications in automated assessments and learning. J Adapt Learn. 2024;39(1):89–104.
- Pandiaraj A. A comparative study on sentiment analysis using ML and DL. In: Advanced Computing Conference Proceedings, 2023, pp. 34–56.
- Borovi F. Comparative analysis of generative AI tools in education. J Comp AI Stud. 2024;13(2):345–67.
- Khosrawi-Rad B, Rinn H, Schlimbach R. Conversational Agents in Education? A Systematic Literature Review. In Proceedings of the 30th European Conference on Information Systems (ECIS), Timi?oara, Romania, 2022.
Cited by
Güler, M. A., Dağ, S., Kayal, S., Can, M., & Şimşekkaya, S. N. (2026) · BMC Medical Education · doi:10.1186/s12909-025-08535-3 · Cited by 6
“The literature suggests that these tools may support learning-related processes (e.g., brainstorming, summarizing, drafting) and time management, while also raising concerns regarding information accuracy, surface-level learning, academic integrity, and data privacy [3].”
Chen, S., & Lou, J. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1727544 · Cited by 2
“Their capacity for individualized feedback and interactive dialogue suggests considerable pedagogical potential (Sharma et al., 2025).”
Bridging the Digital Divide: Socioeconomic Equity in AI-Assisted Hybrid Learning
Poh, R., Tan, B. W., Lee, H. W., & Tan, K. L. (2025) · SN Computer Science · doi:10.1007/s42979-025-04593-y · Cited by 1
Metadata
- Authors
- Sharma, S., Mittal, P., Kumar, M., & Bhardwaj, V.
- Affiliations
- Manipal University Jaipur (IN)
- Amity University (IN)
- Corresponding author
- Bhardwaj, Vivek
- Venue
- Discover Sustainability
- Published
- 2025-04-04
- Volume
- 6
- Issue
- 1
- ISSN
- 2662-9984 (ISSN-L)
- OpenAlex
- W4409189317
- Cited by
- 165
- References
- 42
- Citations by year
- 2026: 118 · 2025: 47
- FWCI
- 25.10
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by-nc-nd
- creativecommons.org/licenses/by-nc-nd/4.0 (tdm)
- creativecommons.org/licenses/by-nc-nd/4.0 (vor)
- Locations
- Discover Sustainability (publishedVersion, cc-by-nc-nd)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Manipal University Jaipur
- Topics
- Social Sciences › Education › Artificial Intelligence in Education
- Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- large language models, personalized learning, artificial intelligence in education, student engagement, emotional and social development, progress monitoring, test fairness, ethical considerations, privacy, accessibility, educational outcomes
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: The role of large language models in personalized learning: a systematic review of educational impact. https://app.cochat.ai/papers/10.1007/s43621-025-01094-z
- The paper
- Sharma, S., Mittal, P., Kumar, M., & Bhardwaj, V. (2025). The role of large language models in personalized learning: a systematic review of educational impact. Discover Sustainability. https://doi.org/10.1007/s43621-025-01094-z
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.