Artificial intelligence (AI) has created new opportunities for improving educational decision-making; however, existing AI-based education systems often lack transparency and personalized intervention capabilities. This study proposes an Explainable Large Language Model (LLM) Framework for Personalized Inclusive Education Interventions in Primary Schools by integrating machine learning, explainable artificial intelligence (XAI), and Retrieval-Augmented Generation (RAG). The framework identifies learners requiring additional educational support and generates evidence-based intervention strategies tailored to individual needs.Publicly available educational datasets from UCI and Kaggle were used to develop predictive models using Random Forest, Support Vector Machine, Artificial Neural Network, LightGBM, CatBoost, and XGBoost algorithms. The proposed Explainable XGBoost-RAG-LLM framework achieved the best performance, demonstrating high predictive accuracy while providing interpretable insights through SHAP and LIME techniques. The explainability analysis identified key factors influencing learner outcomes, including attendance, academic performance, parental support, study behavior, and educational engagement. The RAG-based LLM component transformed predictive results into personalized educational recommendations by integrating evidence from inclusive education guidelines and teaching resources. The proposed framework provides a transparent, scalable, and intelligent decision-support system that assists teachers, administrators, and policymakers in implementing inclusive and personalized education practices.

Explainable AI, Large Language Models, Retrieval-Augmented Generation, Machine Learning, Inclusive Education, Personalized Learning, Educational Data Mining, Learning Analytics, Artificial Intelligence in Education

Adadi, A., & Berrada, M. (2018). Peeking inside the black-box: A survey on explainable artificial intelligence (XAI). IEEE Access, 6, 52138–52160. https://doi.org/10.1109/ACCESS.2018.2870052

Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324

Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D. M., Wu, J., Winter, C., & Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901.

Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785

Cortez, P., & Silva, A. M. G. (2008). Using data mining to predict secondary school student performance. In A. Brito & J. Teixeira (Eds.), Proceedings of the 5th Annual Future Business Technology Conference (pp. 5–12).

Cortez, P. (2008). Student Performance Data Set. UCI Machine Learning Repository. https://archive.ics.uci.edu/ml/datasets/student+performance

Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 4171–4186.

Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5), 1189–1232.

Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.

Holmes, W., Bialik, M., & Fadel, C. (2019). Artificial intelligence in education: Promises and implications for teaching and learning. Center for Curriculum Redesign.

Jamee, S. S., Arif, M., Rahman, M. M., Yassar, I. S., & Hossain, M. A. (2025). Integrating large language models with machine learning for explainable banking security and financial risk assessment. International Interdisciplinary Business Economics Advancement Journal, 6(11), 8–18.

Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T. Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, 30.

Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. International Conference on Learning Representations (ICLR).

Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30.

Mia, M. M., Roy, M. K., Yassar, I. K. M. S., Mottalib, M. Y., Yezdani, S., Majumder Nijhum, A., & Uddin, M. K. (2025). Integrating blockchain security and machine learning for fraud detection in the U.S. banking system. The American Journal of Engineering and Technology, 7(11), 65–76. https://doi.org/10.37547/tajet/Volume07Issue11-08

Molnar, C. (2022). Interpretable machine learning (2nd ed.). https://christophm.github.io/interpretable-ml-book/

Mottalib, M. Y., Nobe, N., Islam, M. T., Hossain, M. R., Jisan, A. H., & Hossen, M. E. (2026). Ensemble machine learning and natural language processing for automated cancer indicator detection in clinical notes. International Journal of Medical Science and Public Health Research, 7(3), 27–37.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, É. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.

Prokhorenkova, L., Gusev, G., Vorobev, A. V., Dorogush, A. V., & Gulin, A. (2018). CatBoost: Unbiased boosting with categorical features. Advances in Neural Information Processing Systems, 31.

Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why should I trust you?": Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1135–1144.

Russell, S., & Norvig, P. (2021). Artificial intelligence: A modern approach (4th ed.). Pearson.

Umam, S., & Razzak, R. B. (2024, October). Linguistic disparities in mental health services: Analyzing the impact of Spanish language support availability in the Saint Louis region, Missouri. In APHA 2024 Annual Meeting and Expo. American Public Health Association.

Umam, S., & Razzak, R. B. (2025, November). A 20-year overview of trends in secondhand smoke exposure among cardiovascular disease patients in the US: 1999–2020. In APHA 2025 Annual Meeting and Expo. American Public Health Association.

UNESCO. (1994). The Salamanca statement and framework for action on special needs education. UNESCO.

UNESCO. (2020). Global education monitoring report 2020: Inclusion and education—All means all. UNESCO Publishing.

UNESCO. (2021). Reimagining our futures together: A new social contract for education. UNESCO Publishing.

UNESCO Institute for Statistics. (2023). SDG 4 data and indicators. https://uis.unesco.org

UNICEF. (2021). Seen, counted, included: Using data to shed light on the well-being of children with disabilities. UNICEF.

United Nations. (2015). Transforming our world: The 2030 agenda for sustainable development. United Nations.

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.

Wang, S., Liu, B., & Zhang, H. (2024). Large language models for education: A systematic review of applications, opportunities, and challenges. Education and Information Technologies. (Please verify final volume, issue, pages, and DOI before submission.)

Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824–24837.

Xie, H., Chu, H. C., Hwang, G. J., & Wang, C. C. (2019). Trends and development in technology-enhanced adaptive learning: A systematic review of journal publications from 2007 to 2017. Computers & Education, 140, 103599.

Yang, L., Yu, Z., & Dillenbourg, P. (2023). Large language models in education: A survey of opportunities and challenges. Computers and Education: Artificial Intelligence, 5, 100173.

Zhang, H., Cissé, M., Dauphin, Y. N., & Lopez-Paz, D. (2018). Mixup: Beyond empirical risk minimization. International Conference on Learning Representations (ICLR).

YASSAR, I. S. (2023). SCALABLE SDN-BASED ARCHITECTURE FOR LARGE-SCALE ENTERPRISE NETWORK MANAGEMENT. Insights Sustainable Engineering Practices, 1(01), 115-130.

YASSAR, I. S. (2024). SECURING US CRITICAL INFRASTRUCTURE WITH AUTONOMOUS LANGUAGE AGENTS: A TRUSTWORTHY, POLICY-ALIGNED FRAMEWORK FOR HIGH-RISK ENTERPRISE REASONING. Journal of Engineering Education and Practice, 2(1), 48-69.

Mia, M. M., Roy, M. K., YASSAR, I. S., Mottalib, M. Y., Yezdani, S., Nijhum, A. M., ... & Uddin, M. K. (2025). Integrating Blockchain Security and Machine Learning for Fraud Detection in the US Banking System. Emerging Frontiers Library for The American Journal of Engineering and Technology, 7(11), 65-76.

YASSAR, I. S. (2026). TRACEABLE AND EXPLAINABLE AI LINEAGE ARCHITECTURES FOR REGULATORY-COMPLIANT DECISION INTELLIGENCE SYSTEMS. Computers and Education Letters, 3(01), 1-18.

Khatun, P., Umam, S., Razzak, R. B., Shamsuddin, I. B., & Salma, N. (2025). A study on the effectiveness of machine learning models for hepatitis prediction. Scientific Reports, 15(1), 30659.

Umam, S., Razzak, R. B., Munni, M. Y., & Rahman, A. (2025). Exploring the non-linear association of daily cigarette consumption behavior and food security-An application of CMP GAM regression. PLoS One, 20(7), e0328109.

Razzak, R. B., & Umam, S. (2025, November). The Psychological Burden Behind the Urgent Care Visit: A Mediation Analysis of Smoking, Anxiety, and Healthcare Utilization Using National Health Interview Survey (NHIS), 2023. In APHA 2025 Annual Meeting and Expo. APHA.