The Convergence of Federated Learning, Knowledge Graphs, and Large Language Models for Language Learning: A Scoping Review
Source abstract
Abstract
Large Language Models (LLMs) in Intelligent Computer-Assisted Language Learning enable highly personalized learning, yet raise significant challenges related to pedagogical grounding, data privacy, and instructional validity. Although Knowledge Graphs (KGs) and Federated Learning (FL) can mitigate these issues in isolation, evidence on systematic FL–KG–LLM integration for educational language learning remains limited. This scoping review maps the FL–KG–LLM convergence landscape. Following PRISMA-ScR guidelines, we searched six databases and screened 51 papers (2019–2025) using automated extraction. Our findings indicate limited convergence: no papers integrate all three domains, and 58.8% of approaches remain confined to isolated technological silos. Reporting is also uneven across the corpus, with an average “Not Reported” (NR) rate of 84.5%, most notably for privacy mechanisms (92.2%), validation metrics (90.2%), and Common European Framework of Reference for Languages (CEFR) alignment (88.2%). Domain-specific analysis reveals two distinct patterns: inter-domain gaps (disciplinary silos resulting in expected CEFR absence in single-domain papers) and intra-domain gaps (failure to report domain-critical variables, including 100% parameter NR in FL studies, 86.7% validation NR in KG studies, and 100% CEFR NR in convergence papers). Taken together, these gaps suggest that pedagogical grounding is treated as optional rather than structural. We therefore identify two pillars of pedagogical grounding: a Grounding Pillar, which constrains LLM outputs via Knowledge Graph rules, and a Validation Pillar, which concerns how authoritative frameworks (e.g., CEFR) are mapped onto Knowledge Graph schemas and evaluated. The near-universal absence of CEFR alignment and validation reporting suggests that this second pillar is currently missing, which we term the Integrity Gap—a systematic disconnection between technological innovation and pedagogical grounding inin Intelligent Computer-Assisted Language Learning. By reframing the problem as upstream control and validation, this review informs the design of user-facing automated systems where trust, transparency, and human oversight are critical.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Innovative Teaching and Learning Methods · Advanced Graph Neural Networks · Intelligent Tutoring Systems and Adaptive Learning
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Cultural Technology and Communication, University of the Aegean, 81100 Mytilene, Greece
References (52)
Show source-provided references
1. Bonawitz, K., Eichner, H., Grieskamp, W., Huba, D., Ingerman, A., Ivanov, V., Kiddon, C., Konečný, J., Mazzocchi, S., and McMahan, H.B. (April, January 31). Towards federated learning at scale: System design. Proceedings of the 2nd SysML Conference, Palo Alto, CA, USA. Available online: https://proceedings.mlsys.org/paper_files/paper/2019/hash/7b770da633baf74895be22a8807f1a8f-Abstract.html.
2. Advances and open problems in federated learning10.1561/2200000083 ↗
3. McMahan, H.B., Moore, E., Ramage, D., Hampson, S., and Arcas, B.A.Y. (2017, January 20–22). Communication-efficient learning of deep networks from decentralized data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017), Fort Lauderdale, FL, USA. Available online: https://proceedings.mlr.press/v54/mcmahan17a.html.
4. Federated learning: Challenges, methods, and future directions
5. Council of Europe (2020). Common European Framework of Reference for Languages: Learning, Teaching, Assessment—Companion Volume, Council of Europe Publishing. Available online: https://www.coe.int/en/web/common-european-framework-reference-languages.
6. Knowledge graphs10.1145/3447772 ↗
7. Bahroun, Z., Anane, C., Ahmed, V., and Zacca, A. (2023). Transforming education: A comprehensive review of generative artificial intelligence in educational settings through bibliometric and content analysis. Sustainability, 15.10.3390/su151712983 ↗
8. ChatGPT for good? On opportunities and challenges of large language models for education10.1016/j.lindif.2023.102274 ↗
9. Bender, E.M., Gebru, T., McMillan-Major, A., and Shmitchell, S. (2021, January 3–10). On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?. Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency (FAccT ’21), Virtual Event.10.1145/3442188.3445922 ↗
10. Brown, T.B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., and Askell, A. (2020, January 6–12). Language models are few-shot learners. Proceedings of the Advances in Neural Information Processing Systems 33 (NeurIPS 2020), Virtual. Available online: https://proceedings.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html.
11. Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., and Metzler, D. (2022). Emergent abilities of large language models. arXiv.
12. Vygotsky, L.S. (1978). Mind in Society: The Development of Higher Psychological Processes, Harvard University Press. Available online: https://www.hup.harvard.edu/books/9780674576292.
13. Kung, T.H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., and Maningo, J. (2023). Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models. PLoS Digit. Health, 2.10.1371/journal.pdig.0000198 ↗
14. Flora: Low-Rank Adapters Are Secretly Gradient Compressors
15. Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W. (2022, January 25–29). LoRA: Low-rank adaptation of large language models. Proceedings of the 10th International Conference on Learning Representations (ICLR 2022), Virtual Event. Available online: https://openreview.net/forum?id=nZeVKeeFYf9.
16. Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C.L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., and Ray, A. (December, January 28). Training language models to follow instructions with human feedback. Proceedings of the Advances in Neural Information Processing Systems 35 (NeurIPS 2022), New Orleans, LA, USA. Available online: https://proceedings.neurips.cc/paper_files/paper/2022/hash/b1efde53be364a73914f58805a001731-Abstract.html.
17. Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., and Scialom, T. (2023). Toolformer: Language models can teach themselves to use tools. arXiv.
18. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., and Rocktäschel, T. (2020, January 6–12). Retrieval-augmented generation for knowledge-intensive NLP tasks. Proceedings of the Advances in Neural Information Processing Systems 33 (NeurIPS 2020), Virtual. Available online: https://proceedings.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html.
19. Nogueira, R., Jiang, Z., Pradeep, R., and Lin, J. (2020, January 16–19). Document ranking with a pretrained sequence-to-sequence model. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2020, Online.10.18653/v1/2020.findings-emnlp.63 ↗
20. Scoping studies: Towards a methodological framework10.1080/1364557032000119616 ↗
21. Scoping studies: Advancing the methodology10.1186/1748-5908-5-69 ↗
22. Updated methodological guidance for the conduct of scoping reviews10.11124/JBIES-20-00167 ↗
23. PRISMA Extension for Scoping Reviews (PRISMA-ScR): Checklist and Explanation10.7326/M18-0850 ↗
24. The PRISMA 2020 statement: An updated guideline for reporting systematic reviews10.1136/bmj.n71 ↗
25. Federated machine learning: Concept and applications
26. Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H.B., Patel, S., Ramage, D., Sadin, A., and Smith, N. (November, January 30). Practical Secure Aggregation for Privacy-Preserving Machine Learning. Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security (CCS), Dallas, TX, USA.10.1145/3133956.3133982 ↗
27. Buscemi, A., and Proverbio, D. (2024). RogueGPT: Dis-ethical tuning transforms ChatGPT-4 into a Rogue AI in 158 Words. arXiv.
28. Meurers, D. (2012). Natural language processing and language learning. The Encyclopedia of Applied Linguistics, Blackwell Publishing. Available online: https://onlinelibrary.wiley.com/doi/10.1002/9781405198431.wbeal0858.pub2.10.1002/9781405198431.wbeal0858 ↗
29. Bosselut, A., Rashkin, H., Sap, M., Malaviya, C., Celikyilmaz, A., and Choi, Y. (August, January 28). COMET: Commonsense transformers for automatic knowledge graph construction. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), Florence, Italy.10.18653/v1/P19-1470 ↗
30. Speer, R., Chin, J., and Havasi, C. (2017, January 4–9). ConceptNet 5.5: An open multilingual graph of general knowledge. Proceedings of the AAAI Conference on Artificial Intelligence, San Francisco, CA, USA. Available online: https://conceptnet.io/.10.1609/aaai.v31i1.11164 ↗
31. Wang, X., He, X., Cao, Y., Liu, M., and Chua, T.-S. (2019, January 4–8). KGAT: Knowledge graph attention network for recommendation. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.10.1145/3292500.3330989 ↗
32. The third AI summer: AAAI Robert S. Engelmore memorial lecture
33. PRISMA-S: An extension to the PRISMA statement for reporting literature searches in systematic reviews10.1186/s13643-020-01542-z ↗
34. Tono, Y., and Negishi, M. (2026, February 23). The CEFR-J: A New Platform for Constructing a Standardized Framework for English Language Education in Japan. Available online: https://www.cefr-j.org/research_eng.html.
35. McCrae, J.P., Rademaker, A., Rudnicka, E., and Bond, F. (2020, January 11–16). English WordNet 2020: Improving and extending a WordNet for English using an open-source methodology. Proceedings of the LREC 2020 Workshop on Multiword Expressions, Marseille, France. Available online: https://github.com/globalwordnet/english-wordnet.
36. Dürlich, L., and François, T. (2018, January 7–12). EFLLex: A graded lexicon of general English for foreign language learners. Proceedings of the 11th International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. Available online: https://cental.uclouvain.be/cefrlex/efllex/.
37. Babakniya, S., Elkordy, A.R., Ezzeldin, Y.H., Liu, Q., Kim, S., Avestimehr, S., and Dhillon, S. (2023). SLORA: Federated parameter efficient fine-tuning of language models. arXiv.
38. The English Grammar Profile of learner competence: Methodology and key findings
39. Kenton, Z., Everitt, T., Weidinger, L., Gabriel, I., Mikulik, V., and Irving, G. (2021). Alignment of language agents. arXiv.
40. Paraphrase acquisition via crowdsourcing and machine learning10.1145/2483669.2483676 ↗
41. Tayyeh, M., and AL-Jumaili, H.K. (2024). Balancing Privacy and Performance: A Differential Privacy Approach in Federated Learning. Computers, 13.10.3390/computers13110277 ↗
42. Wang, Z., Shen, Z., He, Y., Sun, G., Wang, H., Lyu, L., and Li, A. (2024, January 10–15). FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations. Proceedings of the Advances in Neural Information Processing Systems 37 (NeurIPS 2024), Vancouver, BC, Canada.
43. Song, J., Wang, S., Shun, J., and Zhu, Y. (2025). Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning. arXiv.
44. Edge, D., Trinh, H., Cheng, N., Bradley, J., Chao, A., Mody, A., Truitt, S., Metropolitansky, D., Ness, R.O., and Larson, J. (2024). From Local to Global: A Graph RAG Approach to Query-Focused Summarization. arXiv.
45. Knowledge Graphs as a Source of Trust for LLM-Powered Enterprise Question Answering10.1016/j.websem.2024.100858 ↗
46. The algorithmic foundations of differential privacy10.1561/0400000042 ↗
47. Munn, Z., Peters, M.D.J., Stern, C., Tufanaru, C., McArthur, A., and Aromataris, E. (2018). Systematic review or scoping review? Guidance for authors when choosing between a systematic or scoping review approach. BMC Med. Res. Methodol., 18.10.1186/s12874-018-0611-x ↗
48. Srinivasan, A., Berkowitz, J., Kivelson, S., Friedrich, N., and Tatonetti, N. (2025). Large-scale Evaluation of Reporting Quality in 21,041 Randomized Trials (1966–2024). medRxiv, preprint.
49. Compliance with Preferred Reporting Items for Systematic Review and Meta-Analysis Individual Participant Data Statement for Meta-Analyses Published for Stroke Studies10.1161/STROKEAHA.120.033288 ↗
50. Fanous, A., Goldberg, J., Agarwal, A.A., Lin, J., Zhou, A., Daneshjou, R., and Koyejo, S. (2025, January 20–22). SycEval: Evaluating LLM Sycophancy. Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (AIES 2025), Madrid, Spain. Available online: https://ojs.aaai.org/index.php/AIES/article/view/36598.
51. Human-centered ontology engineering: The HCOME methodology10.1007/s10115-005-0227-4 ↗
52. Neural-Symbolic Methods for Knowledge Graph Reasoning: A Survey10.1145/3686806 ↗