EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Open-Source Large Language Models in Education: A Narrative Review of Evidence, Pedagogical Roles, and Learning Outcomes

Michael Pin-Chuan Lin, Jing-Yuan Huang, Daniel H. Chang, Gerald Tembrevilla, G. Michael Bowen, Eric Poitras, Vasudevan Janarthanan, Jeeho Ryoo

AI in Education · 27.02.2026 · 2 (1) · 4

DOI: 10.3390/aieduc2010004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AI in Education, online erschienen am 27.02.2026. Verfasst von Michael Pin-Chuan Lin und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Social Sciences and Humanities Research Council of Canada.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Open-source large language models (LLMs) are increasingly explored in educational contexts due to their transparency, adaptability, and alignment with institutional governance and equity considerations. Despite growing interest, empirical research on how open-source LLMs are deployed in education and what evidence currently supports their integration remains limited and fragmented. This paper presents a state-of-the-art narrative review of peer-reviewed, human empirical studies examining the use of open-source LLMs in education. Guided by three questions, the review synthesizes how open-source LLMs are deployed across instructional contexts, what learner-related evidence is reported, and how teachers engage in human–AI collaboration. The reviewed literature is concentrated in higher education, particularly within computer science and programming domains, with applications focused on post-class tutoring, guidance, and formative feedback. Learner perceptions are generally positive, but evidence linking open-source LLM use to measurable learning outcomes remains emerging and inconsistent. Through interpretive synthesis, the review articulates a four-role model—Designer, Facilitator, Monitor, and Evaluator—that captures how teacher agency is enacted across AI-supported instructional workflows. This review maps recurring orchestration dimensions, decision points, and tensions that characterize early implementations, and it proposes a minimal orchestration reporting scaffold (configuration, boundaries, logging, adjudication) intended to support auditability and cross-study comparison as the empirical base develops.

Förderung

  • Social Sciences and Humanities Research Council of Canada

Zitieren

APA

Lin, M. P., Huang, J., Chang, D. H., Tembrevilla, G., Bowen, G. M., Poitras, E., Janarthanan, V., & Ryoo, J. (2026). Open-Source Large Language Models in Education: A Narrative Review of Evidence, Pedagogical Roles, and Learning Outcomes. AI in Education, 2(1), 4. https://doi.org/10.3390/aieduc2010004

Vancouver

Lin MP, Huang J, Chang DH, Tembrevilla G, Bowen GM, Poitras E, et al. Open-Source Large Language Models in Education: A Narrative Review of Evidence, Pedagogical Roles, and Learning Outcomes. AI in Education. 2026;2(1):4. doi:10.3390/aieduc2010004

BibTeX
@article{Lin2026,
  author = {Lin, Michael Pin-Chuan and Huang, Jing-Yuan and Chang, Daniel H. and Tembrevilla, Gerald and Bowen, G. Michael and Poitras, Eric and Janarthanan, Vasudevan and Ryoo, Jeeho},
  title = {Open-Source Large Language Models in Education: A Narrative Review of Evidence, Pedagogical Roles, and Learning Outcomes},
  journal = {AI in Education},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {4},
  doi = {10.3390/aieduc2010004}
}
Kostenlos starten →