Unlocking the Black Box: Explainable Artificial Intelligence (XAI) for Trust and Transparency in AI Systems

Nipuna Sankalpa Thalpage

Cardiff Metropolitan University, UK

Cite: Thalpage N.S. Unlocking the Black Box: Explainable Artificial Intelligence (XAI) for Trust and Transparency in AI Systems. J. Digit. Art Humanit. 4(1), 31-36, (2023). https://doi.org/10.33847/2712-8148.4.1_4

Abstract. Explainable Artificial Intelligence (XAI) has emerged as a critical field in AI research, addressing the lack of transparency and interpretability in complex AI models. This conceptual review explores the significance of XAI in promoting trust and transparency in AI systems. The paper analyzes existing literature on XAI, identifies patterns and gaps, and presents a coherent conceptual framework. Various XAI techniques, such as saliency maps, attention mechanisms, rule-based explanations, and model-agnostic approaches, are discussed to enhance interpretability. The paper highlights the challenges posed by black-box AI models, explores the role of XAI in enhancing trust and transparency, and examines the ethical considerations and responsible deployment of XAI. By promoting transparency and interpretability, this review aims to build trust, encourage accountable AI systems, and contribute to the ongoing discourse on XAI.
Key words: Explainable Artificial Intelligence, Black Box AI, Conceptual framework.


  1. Colley, K. Väänänen and J. Häkkilä,, “Tangible Explainable AI – an Initial Conceptual Framework,” in 21th International Conference on Mobile and Ubiquitous Multimedia, Lisbon, 2022. 
  2. Holzinger, G. Langs and H. Denk, “Causability and explainabilty of artificial intelligence in medicine,” Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, July 2019. 
  3. M. Ghassemi, . O.-R. Luke and . A. L. Beam, “The false hope of current approaches to explainable artificial intelligence in health care,” The Lancet Digital Health, November 2021. 
  4. G. Schwalbe and B. Finzel, “A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts,” Data Mining and Knowledge Discovery , 2021. 
  5. J. Jiménez-Luna and F. Grisoni, “Drug discovery with explainable artificial intelligence,” Nature Machine Intelligence, 2020. 
  6. A. Heuillet, F. Couthouis and N. Díaz-Rodríguez, “Explainability in deep reinforcement learning,” Knowledge-Based Systems 214(7540):106685, 2020. 
  7. P. P. Angelov, E. A. Soares and R. Jiang, “Explainable artificial intelligence: an analytical Review,” Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 11(5), 2021. 
  8. F. K. Došilović, M. Brčić and Nikica Hlupić, “Explainable artificial intelligence: A survey,” in International Convention MIPRO, 2018. 
  9. D. Gunning, M. Stefik and J. Choi, “XAI-Explainable artificial intelligence,” Science Robotics, 2019. 
  10. Michael Ridley, “Explainable Artificial Intelligence (XAI),” Information Technology and Libraries, 2022. 
  11. S. Jagati, “AI’s black box problem: Challenges and solutions for a transparent future,” May 2023. [Online]. Available: https://cointelegraph.com/news/ai-s-black-box-problem-challenges-and-solutions-for-a-transparent-future.
  12. P. Linardatos, V. Papastefanopoulos, and S. Kotsiantis, “Explainable AI: A Review of Machine Learning Interpretability Methods,” Entropy (Basel), December 2020. 
  13. Kinza Yasar, “black box AI,” March 2023. [Online]. Available: https://www.techtarget.com/whatis/definition/black-box-AI.
  14. L. Blouin, “AI’s mysterious ‘black box’ problem, explained,” 2023. [Online]. Available: https://umdearborn.edu/news/ais-mysterious-black-box-problem-explained.
  15. Rudin C., and . J. Radin, “Why Are We Using Black Box Models in AI When We Don’t Need To? A Lesson From an Explainable AI Competition,” 2019. [Online]. 
  16. K. Simonyan, A. Vedaldi and A. Zisserman, “Deep Inside Convolutional Networks: Visualising,” 2013. 
  17. Bahdanau, K. Cho and Y. Bengio, “Neural Machine Translation by Jointly Learning to Align and Translate,” 2014. 
  18. M. T. Ribeiro, S. Singh and C. Guestrin, “”Why Should I Trust You?”: Explaining the Predictions of Any Classifier,” in the 22nd ACM SIGKDD International Conference, 2016. 
  19. S. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions,” in 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA., 2017. 
  20. A. Adadi and M. Berrada, “Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI),” IEEE Access, 2018. 
  21. B. Arrieta, N. D.-. Rodríguez and J. Del Ser, “Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI,” Information Fusion 58, 2019. 
  22. R. Guidotti, A. Monreale and F. Turini, “A Survey of Methods for Explaining Black Box Models,” ACM Computing Surveys , 2018. 
  23. A. Rajkomar, E. Oren and K. Chen, “Scalable and accurate deep learning for electronic health records,” Digital Medicine 1(1), 2018. 
  24. Owens, B. Sheehan and M. Mullins, “Explainable Artificial Intelligence (XAI) in Insurance,” Risks, 2022. 
  25. Z. C. Lipton, “The Mythos of Model Interpretability,” Communications of the ACM 61(10), 2016. 
  26. J. Burrell, “How the machine ‘thinks: Understanding opacity in machine learning algorithms,” Big Data & Society 3(1, January 2016. 
  27. Goodman and S. Flaxman, “EU regulations on algorithmic decision-making and a “right to explanation”,” Ai Magazine 38(3), 2016. 
  28. Pedreschi, F. Giannotti, R. Guidotti, A. Monreale, S. Ruggieri and F. Turini, “Meaningful Explanations of Black Box AI Decision Systems,” Proceedings of the AAAI Conference on Artificial Intelligence, 2019. 
  29. A. Jobin, M. Ienca and E. Vayena, “Artificial Intelligence: the global landscape of ethics guidelines,” 2019. 
  30. S. Arora and P. Rajan, “Explainable AI for finance: A review,” Journal of Big Data.

Published online 26.06.2023