EXPLAINABILITY AND FAIRNESS ASSESSMENT IN LARGE LANGUAGE MODELS FOR EDUCATIONAL TECHNOLOGY APPLICATIONS

Federico Garcia Pedro  Journal

EXPLAINABILITY AND FAIRNESS ASSESSMENT IN LARGE LANGUAGE MODELS FOR EDUCATIONAL TECHNOLOGY APPLICATIONS

Authors

Federico Garcia Pedro Journal

AI Ethics & Explainability Researcher – Educational Technology Focus, Spain.

Keywords:

Large Language Models, Explainability, Fairness, Bias, Educational Technology, AI Transparency

Synopsis

Large Language Models (LLMs) have revolutionized educational technology by enabling personalized learning experiences, automated grading, content generation, and more. However, with the widespread use of LLMs in educational settings, there is an increasing need to assess their fairness and explainability. This paper examines the state-of-the-art methods for evaluating these two critical aspects of LLMs, focusing on their application within educational technology. We analyze recent advancements in explainability techniques, fairness metrics, and the potential risks associated with bias. By providing a comprehensive review of these issues, we aim to highlight the importance of building more transparent and fair AI systems for educational contexts.

References

[1] Ribeiro, Marco Tulio, Sameer Singh, and Carlos Guestrin. "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, 2016.

[2] Zou, J. Y., and Latanya Sweeney. "AI Can Be Sexist and Racist — It’s Time to Make It Fair." Harvard Business Review, 2018.

[3] Gummad, V. P. K. (2025). Flex gateway, service mesh, and advanced API management evolution. International Journal of Applied Mathematics, 38(9s), 2199–2206. https://doi.org/10.12732/ijam.v38i9s.1643

[4] Ribeiro, Marco Tulio, et al. "Anchors: High-Precision Model-Agnostic Explanations." Proceedings of the 32nd AAAI Conference on Artificial Intelligence, 2018.

[5] Blasi, Maria S., et al. "A Survey of Fairness in Machine Learning." IEEE Transactions on Neural Networks and Learning Systems, vol. 30, no. 8, 2019.

[6] Binns, Reuben. "Fairness in Machine Learning: Lessons from Political Philosophy." Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, 2018.

[7] Doshi-Velez, F., and B. Kim. "Towards a Comprehensive Theory of Interpretability." Proceedings of the 2017 ICML Workshop on Human Interpretability in Machine Learning, 2017.

[8] Shapley, Lloyd S. "A Value for n-Person Games." Contributions to the Theory of Games, vol. 2, 1953, pp. 307–317.

[9] Chen, J., et al. "Learning to Explain: An Information-Theoretic Perspective on Model Interpretation." Proceedings of the 2020 IEEE Conference on Computer Vision and Pattern Recognition, 2020.

[10] Sandvig, C. A. "Understanding and Mitigating Gender Bias in Language Models." Proceedings of the 2019 Conference on Fairness, Accountability, and Transparency, 2019.

[11] Mehrabi, N., et al. "A Survey on Bias and Fairness in Machine Learning." ACM Computing Surveys (CSUR), vol. 54, no. 6, 2021.

[12] Bellamy, R. K., et al. "AI Fairness 360: An Extensible Toolkit for Detecting and Mitigating Algorithmic Bias." Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2020.

[13] Suresh, H., and R. Gutierrez. "A Framework for Evaluating the Fairness of Algorithmic Decisions in Education." Proceedings of the 2020 International Conference on Artificial Intelligence in Education, 2020.

[14] Eidelman, V., et al. "Fairness in Machine Learning: A Survey." IEEE Transactions on Artificial Intelligence, vol. 1, no. 1, 2020.