Keywords:-
Article Content:-
Abstract
Explainable Artificial Intelligence (XAI) has become increasingly essential in distance learning systems, where predictive models are used to support assessment, personalised feedback, learner monitoring, and early-warning interventions. Local Interpretable Model-Agnostic Explanations (LIME) is a widely adopted XAI techniques due to its model flexibility and ease of implementation. However, LIME suffers from methodological limitations and limited global interpretability, that undermine its suitability for high-stakes educational applications. This systematic literature review analysed research published on LIME optimisation, categorising existing enhancements into six major strategy groups: deterministic and uncertainty-based sampling, data-aware perturbations, nonlinear surrogate models, global and aggregated explainability methods, visual and relational interpretation enhancements, and hybrid or optimisation-driven frameworks. Findings show that while numerous variants significantly improve stability, fidelity, or interpretability within their respective domains, most remain domain-specific, computationally demanding, and insufficiently evaluated through human-centred or educational lenses. Only a few studies explore LIME optimisation within learning analytics, leaving a substantial gap in applying enhanced XAI methods to distance learning environments. The review identifies unresolved challenges like the need for multimodal and sequential data handling, unified optimisation across multiple objectives, scalable real-time implementation, and empirically validated human interpretability. Insights from literature inform a set of design requirements for an improved LIME-based XAI system designed for distance learning.
References:-
References
Abdullah, T. A. A., Zahid, M. S. M., Turki, A. F., Ali, W., Jiman, A. A., Abdulaal, M. J., ... & Attar, E. T. (2024). Sig-lime: A signal-based enhancement of lime explanation technique. IEEE access, 12, 52641-52658.
Abdullah, T. A., Zahid, M. S. M., Ali, W., & Hassan, S. U. (2023). B-LIME: An improvement of LIME for interpretable deep learning classification of cardiac arrhythmia from ECG signals. Processes, 11(2), 595.
Ahern, I., Noack, A., Guzman-Nateras, L., Dou, D., Li, B., & Huan, J. (2019). NormLime: A new feature importance metric for explaining deep neural networks. arXiv preprint arXiv:1909.04200.
An, J., Zhang, Y., & Joe, I. (2023). Specific-input lime explanations for tabular data based on deep learning models. Applied Sciences, 13(15), 8782.
Angiulli, F., De Luca, F., Fassetti, F., & Nisticò, S. (2025). LLiMe: enhancing text classifier explanations with large language models. Machine Learning, 114(12), 271.
Bacevicius, M., Paulauskaite-Taraseviciene, A., Zokaityte, G., Kersys, L., & Moleikaityte, A. (2025). Comparative analysis of perturbation techniques in LIME for intrusion detection enhancement. Machine Learning and Knowledge Extraction, 7(1), 21.
Bora, R. P., Terhörst, P., Veldhuis, R., Ramachandra, R., & Raja, K. (2024). Slice: Stabilized lime for consistent explanations for image classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10988-10996).
Botari, T., Hvilshøj, F., Izbicki, R., & de Carvalho, A. C. (2020). MeLIME: Meaningful local explanation for machine learning models. arXiv preprint arXiv:2009.05818.
Bramhall, S., Horn, H., Tieu, M., & Lohia, N. (2020). Qlime-a quadratic local interpretable model-agnostic explanation approach. SMU Data Science Review, 3(1), 4.
Dehghani, Z., Aslansefat, K., Khan, A., & Akram, M. N. (2025). Explainability of Large Language Models using SMILE: Statistical Model-agnostic Interpretability with Local Explanations. arXiv preprint arXiv:2505.21657.
Dikopoulou, Z., Moustakidis, S., & Karlsson, P. (2021). GLIME: A new graphical methodology for interpretable model-agnostic explanations. arXiv preprint arXiv:2107.09927.
Duong, H., Hoang, L., & Le, B. (2023, October). Controlling lime kernel width to achieve comprehensible explanations on tabular data. In International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making (pp. 153-164). Cham: Springer Nature Switzerland.
ElShawi, R., Sherif, Y., Al-Mallah, M., & Sakr, S. (2019, August). Ilime: Local and global interpretable model-agnostic explainer of black-box decision. In European Conference on Advances in Databases and Information Systems (pp. 53-68). Cham: Springer International Publishing.
Garcia, W., Chen, P. Y., Clouse, H. S., Jha, S., & Butler, K. R. (2023, February). Less is more: Dimension reduction finds on-manifold adversarial examples in hard-label attacks. In 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) (pp. 254-270). IEEE.
Gaudel, R., Galárraga, L., Delaunay, J., Rozé, L., & Bhargava, V. (2022, April). s-LIME: Reconciling locality and fidelity in linear explanations. In International Symposium on Intelligent Data Analysis (pp. 102-114). Cham: Springer International Publishing.
Gonzalez, A. V., & Søgaard, A. (2020). The reverse turing test for evaluating interpretability methods on unknown tasks. In NeurIPS 2020 Workshop on Human And Model in the Loop Evaluation and Training Strategies.
Hassija, V., Chamola, V., Mahapatra, A., Singal, A., Goel, D., Huang, K., ... & Hussain, A. (2024). Interpreting black-box models: a review on explainable artificial intelligence. Cognitive Computation, 16(1), 45-74.
Holm, S., & Macedo, L. (2023, July). The accuracy and faithfullness of AL-DLIME-active learning-based deterministic local interpretable model-agnostic explanations: A comparison with LIME and DLIME in medicine. In World Conference on Explainable Artificial Intelligence (pp. 582-605). Cham: Springer Nature Switzerland.
Hryniewska, W., Grudzień, A., & Biecek, P. (2024). LIMEcraft: handcrafted superpixel selection and inspection for Visual eXplanations. Machine Learning, 113(5), 3143-3160.
Hu, L., Chen, J., Nair, V. N., & Sudjianto, A. (2018). Locally interpretable models and effects based on supervised partitioning (LIME-SUP). arXiv preprint arXiv:1806.00663.
Hung, Y. H., & Lee, C. Y. (2024). BMB-LIME: LIME with modeling local nonlinearity and uncertainty in explainability. Knowledge-Based Systems, 294, 111732.
Knab, P., Marton, S., & Bartelt, C. (2024). Dseg-lime–improving image explanation by hierarchical data-driven segmentation. arXiv preprint arXiv:2403.07733.
Knab, P., Marton, S., Schlegel, U., & Bartelt, C. (2025, July). Which lime should i trust? concepts, challenges, and solutions. In World Conference on Explainable Artificial Intelligence (pp. 28-52). Cham: Springer Nature Switzerland.
Kovalev, M. S., Utkin, L. V., & Kasimov, E. M. (2020). SurvLIME: A method for explaining machine learning survival models. Knowledge-Based Systems, 203, 106164.
Laguna, S., Heidenreich, J. N., Sun, J., Cetin, N., Al-Hazwani, I., Schlegel, U., ... & El-Assady, M. (2023, October). ExpLIMEable: A visual analytics approach for exploring LIME. In 2023 Workshop on Visual Analytics in Healthcare (VAHC) (pp. 27-33). IEEE.
Li, X., Xiong, H., Li, X., Zhang, X., Liu, J., Jiang, H., ... & Dou, D. (2024, February). G-LIME: statistical learning for local interpretations of deep neural networks using global priors (abstract reprint). In Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence (pp. 22705-22705).
Lyu, Y., Liang, P. P., Deng, Z., Salakhutdinov, R., & Morency, L. P. (2022, July). Dime: Fine-grained interpretations of multimodal models via disentangled local explanations. In Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society (pp. 455-467).
Mulwa, M. M., Mwangi, R. W., & Mindila, A. (2024). GMM‐LIME explainable machine learning model for interpreting sensor‐based human gait. Engineering Reports, 6(10), e12864.
Nnadi, L. C., Watanobe, Y., Rahman, M. M., & John-Otumu, A. M. (2024). Prediction of students’ adaptability using explainable AI in educational machine learning models. Applied Sciences, 14(12), 5141.
Rabold, J., Deininger, H., Siebers, M., & Schmid, U. (2019, September). Enriching visual with verbal explanations for relational concepts–combining LIME with Aleph. In Joint European conference on machine learning and knowledge discovery in databases (pp. 180-192). Cham: Springer International Publishing.
Rahimiaghdam, S., & Alemdar, H. (2025). MindfulLIME: A Stable Solution for Explanations of Machine Learning Models with Enhanced Localization Precision--A Medical Image Case Study. arXiv preprint arXiv:2503.20758.
Raza, S., Fatima, I., Arif, S., Sharif, M., Jalal, M. S., & Muhammad, Z. (2024). The future of learning: building trust and transparency in AI education. Journal of management practices, humanities and social sciences., 8(3), 62-74.
Recio-García, J. A., Díaz-Agudo, B., & Pino-Castilla, V. (2020, June). CBR-LIME: a case-based reasoning approach to provide specific local interpretable model-agnostic explanations. In International Conference on Case-Based Reasoning (pp. 179-194). Cham: Springer International Publishing.
Saadatfar, H., Kiani-Zadegan, Z., & Ghahremani-Nezhad, B. (2024). US-LIME: Increasing fidelity in LIME using uncertainty sampling on tabular data. Neurocomputing, 597, 127969.
Saadatfar, H., Kiani-Zadegan, Z., & Ghahremani-Nezhad, B. (2024). US-LIME: Increasing fidelity in LIME using uncertainty sampling on tabular data. Neurocomputing, 597, 127969.
Salgotra, R., & Gandomi, A. H. (2024). A novel multi-hybrid differential evolution algorithm for optimization of frame structures. Scientific Reports, 14(1), 4877.
Salgotra, R., Lamba, A. K., Talwar, D., Gulati, D., & Gandomi, A. H. (2024). A hybrid swarm intelligence algorithm for region-based image fusion. Scientific Reports, 14(1), 13723.
Sangroya, A., Rastogi, M., Anantaram, C., & Vig, L. (2020, October). Guided-LIME: Structured Sampling based Hybrid Approach towards Explaining Blackbox Machine Learning Models. In CIKM (Workshops) (Vol. 17).
Shankaranarayana, S. M., & Runje, D. (2019, October). ALIME: Autoencoder based approach for local interpretability. In International conference on intelligent data engineering and automated learning (pp. 454-463). Cham: Springer International Publishing.
Sivill, T., & Flach, P. (2022, May). Limesegment: Meaningful, realistic time series explanations. In International Conference on Artificial Intelligence and Statistics (pp. 3418-3433). PMLR.
Snoek, J., Larochelle, H., & Adams, R. P. (2012). Practical bayesian optimization of machine learning algorithms. Advances in neural information processing systems, 25.
Sokol, K., & Flach, P. (2025). LIMEtree: Consistent and faithful surrogate explanations of multiple classes. Electronics, 14(5), 929.
Sokol, K., Hepburn, A., Santos-Rodriguez, R., & Flach, P. (2019). bLIMEy: surrogate prediction explanations beyond LIME. arXiv preprint arXiv:1910.13016.
Stadler, A., Müller, W. G., & Harman, R. (2025). Green LIME: Improving AI Explainability through Design of Experiments. arXiv preprint arXiv:2502.12753.
Tan, L., Huang, C., & Yao, X. (2025). A Faithful and Stable Explanation Method for Image Classification. IEEE Transactions on Emerging Topics in Computational Intelligence.
Tan, Z., Tian, Y., & Li, J. (2023). GLIME: General, stable and local LIME explanation. Advances in Neural Information Processing Systems, 36, 36250-36277.
Utkin, L. V., Kovalev, M. S., & Kasimov, E. M. (2020, September). An explanation method for black-box machine learning survival models using the Chebyshev distance. In Conference on Artificial Intelligence and Natural Language (pp. 62-74). Cham: Springer International Publishing.
Visani, G., Bagli, E., & Chesani, F. (2020). Optilime: Optimized lime explanations for diagnostic computer algorithms. arXiv preprint arXiv:2006.05714.
Wang, G., Wang, H., Lv, S., Kang, X., & Cui, Q. A. (2025). Explainable artificial intelligence for manufacturing process modelling and optimisation: an integrated ANN and LIME approach. International Journal of Production Research, 1-22.
Yasui, D., & Sato, H. (2025). Improving local fidelity and interpretability of LIME by replacing only the sampling process with CVAE. IEEE Access.
Zafar, M. R., & Khan, N. M. (2019). DLIME: A deterministic local interpretable model-agnostic explanations approach for computer-aided diagnosis systems. arXiv preprint arXiv:1906.10263.