Nipuna Sankalpa Thalpage, Dulanjaya Epa, Sithara Jayawardhana
Cite this article: Thalpage, N.; Epa, D.; Jayawardhana, S. Ethical Challenges in Explainable AI: A Review on Cultural and Social Bias. JDAH 6(1), 30-39, (2025). https://doi.org/10.33847/2712-8148.6.1_3.
Abstract. Explainable Artificial Intelligence (XAI) has emerged as a critical domain within AI research, aiming to enhance system transparency and user trust. While technical advancements in XAI have improved algorithmic interpretability, ethical concerns, particularly cultural and social biases, remain underexplored. This study adopts a semi-systematic literature review approach to examine how ethical challenges, particularly cultural and social biases, are addressed in Explainable AI (XAI) research, based on papers published between 2017 and 2025, focusing on how current XAI systems recognize, reinforce, or attempt to address such biases. The findings indicate a predominant focus on Western user populations, minimal engagement with underrepresented communities, and a lack of participatory or culturally responsive design strategies. By analyzing themes across healthcare, education, and decision-support systems, the review highlights the limitations of existing models and the need for inclusive, user-centered approaches. The paper concludes by proposing research directions centered on localized explanation models, participatory design, and expanded evaluation metrics that account for cultural relevance and social equity. These insights contribute to the ongoing effort to align XAI development with ethical principles and ensure equitable AI outcomes across diverse user groups.
Keywords: Explainable Artificial Intelligence (XAI), Ethical AI, Social Bias, Cultural Bias.
References
1. Thalpage, N. S. “The Integration of Machine Learning and Explainable AI in Business Digitization: Unleashing the Power of Data -A Review,” Journal of Digital Science, 2024. DOI: 10.33847/2686-8296.6.1_2
2. Doran, D.; Schulz Sarah S.; Besold, T. R. What Does Explainable AI Really Mean? A New Conceptualization of Perspectives. DOI: 10.48550/arXiv.1710.00794, 2017.
3. Miller, T. P.; Sonenberg, Howe and L. “Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciences,” no. 10.48550/arXiv.1712.00547, 2017.
4. Zhu, J.; Liapis, A.; Risi, S.; Bidarra R.; Youngblood, G. M. “Explainable AI for Designers: A Human-Centered Perspective on Mixed-Initiative Co-Creation,” no. 10.1109/CIG.2018.8490433, 2018.
5. Peters U. ; Carman, M. Cultural Bias in Explainable AI Research: A Systematic Analysis,” Journal of Artificial Intelligence Research, 79 (2024) 971-1000, 2024. https://doi.org/10.1613/jair.1.14888.
6. Xu T.; Rose, G. Opportunities and Barriers to Artificial Intelligence Adoption in Palliative/Hospice Care for Underrepresented Groups A Technology Acceptance Model–Based Review,” Journal of Hospice & Palliative Nursing, no. DOI: 10.1097/NJH.0000000000001120, 2025.
7. Lecue, F. On the role of knowledge graphs in explainable AI. DOI: 10.3233/SW-190374, 2019. DOI: 10.3233/SW-190374, 2019.
8. Rai, A. Explainable AI: from black box to glass box,” Journal of the Academy of Marketing Science,, no. DOI: 10.1007/s11747-019-00710-5, 2019.
9. Holzinger, A. et al. Explainable AI Methods – A Brief Overview,” Lecture Notes in Computer Science, no. DOI: 10.1007/978-3-031-04083-2_2, 2022.
10. Thalpage N.S. Unlocking the Black Box: Explainable Artificial Intelligence (XAI) for Trust and Transparency in AI Systems. Journal of Digital Art & Humanities. 4(1), 31-36, (2023). https://doi.org/10.33847/2712-8148.4.1_4.
11. Akinrinola, O. et al. Navigating and reviewing ethical dilemmas in AI development: Strategies for transparency, fairness, and accountability. GSC Advanced Research and Reviews, DOI: 10.30574/gscarr.2024.18.3.0088, 2024.
12. Peters U.; Carman, M. Cultural Bias in Explainable AI Research: A Systematic Analysis. The Journal of Artificial Intelligence Research (JAIR), no. https://doi.org/10.1613/jair.1.14888, 2024.
13. Bryan-Kinns N.; Li, Z. Reducing Barriers to the Use of Marginalised Music Genres in A. Explainable AI for the Arts. https://doi.org/10.48550/arXiv.2407.13439 , 2024.
14. Thalpage N. S.; Nisansala, T. A. D. Exploring the Opportunities of Applying Digital Twins for Intrusion Detection in Industrial Control Systems of Production and Manufacturing – A Systematic Review. Data Protection in a Post-Pandemic Society, DOI: 10.1007/978-3-031-34006-2_4 , 2023.
15. Wang, D.; Yang, Q.; Ashraf A.; Lim, B. Designing Theory-Driven User-Centric Explainable AI. 2019. DOI: https://doi.org/10.1145/3290605.3300831
16. Yuan, C. W.; Bi, N.; Lin Y.-F.; Tseng, Y.-H. Contextualizing User Perceptions about Biases for Human-Centered Explainable Artificial Intelligence in CHI ’23: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, 2023. https://doi.org/10.1145/3544548.3580945
17. Shahrzad, H.; Hodjat B.; Miikkulainen, R. EVOTER: Evolution of Transparent Explainable Rule-sets. ACM Transactions on Evolutionary Learning and Optimization, 2025. https://doi.org/10.1145/3702651
18. De-Giorgio, F. et al. The need for balancing ‘black box’ systems and explainable artificial intelligence: A necessary implementation in radiology,” European Journal of Radiology, 2025. DOI: 10.1016/j.ejrad.2025.112014
19. Danry, V.; Pataranutaporn, P.; Mao Y.; Maes, P. Wearable Reasoner: Towards Enhanced Human Rationality Through A Wearable Device With An Explainable AI Assistant, in AHs ’20: Proceedings of the Augmented Humans International Conference, 2020. https://doi.org/10.1145/3384657.3384799
20. Bertrand, A.; Belloum, R.; Eagan J. R.; Maxwell, W. How Cognitive Biases Affect XAI-assisted Decision-making: A Systematic Review, in AIES ’22: Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society, 2022. DOI: 10.1145/3514094.3534164
21. Huang, L. T.-L.; Chen H.-Y.; Lin Y.-T. Ameliorating Algorithmic Bias, or Why Explainable AI Needs Feminist Philosophy in Feminist Philosophy Quarterly, 2022. DOI: 10.5206/fpq/2022.3/4.14347
22. Ziosi, M.; Watson D.; Floridi, L. A Genealogical Approach to Algorithmic Bias. SSRN Electronic Journal, 2024. DOI: 10.1007/s11023-024-09672-2
23. Roozafzai, Z. Navigating Ethical Complexities of Artificial Intelligence in Civil Justice: A Discourse Analysis. Journal of Digital Arts and Humanities. https://doi.org/10.33847/2712-8149.5.2_2.
24. Yadav, B. “The Ethics of Understanding: Exploring Moral Implications of Explainable AI,” International Journal of Science and Research (IJSR), 2024. DOI: 10.21275/SR2452912281
25. Etzioni A.; Etzioni, O. “Incorporating Ethics into Artificial Intelligence,” The Journal of Ethics. DOI: 10.1007/s10892-017-9252-2
26. Andrade O. M. d.; Alves, M. A. S. “From ‘black box’ to ‘glass box’: using Explainable Artificial Intelligence (XAI) to reduce opacity and address bias in algorithmic models,” Revista Thesis Juris, 2024. DOI: 10.5585/13.2024.26510
27. Antoniadi, A. M.; et al. “Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review”,” Applied Sciences, 2021. https://doi.org/10.3390/app11115088
28. Mahsan Nourani, C. R.; Block, J. E.; Honeycutt D. R.; Rahman, T. “On the Importance of User Backgrounds and Impressions: Lessons Learned from Interactive AI Applications,” ACM Transactions on Interactive Intelligent Systems, 2022. DOI: 10.1145/3531066
29. Ziosi, M.; Watson D.; Floridi, L. “A Genealogical Approach to Algorithmic Bias,” SSRN Electronic Journal, 2024. 10.1007/s11023-024-09672-2
30. Rosenbacke, R.; Melhus, A.; Mckee, M.; Stuckler, D. “How Explainable Artificial Intelligence Can Increase or Decrease Clinicians’ Trust in AI Applications in Health Care: Systematic Review,” JMIR AI, 2024. https://doi.org/10.2196/53207
31. Zhang, Z. H. Al and HamadiHussam, “Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research,” IEEE Access, 2022. DOI: 10.1109/ACCESS.2022.3204051
32. Stahl, B. C.; et al. A systematic review of artificial intelligence impact assessments. Artificial Intelligence Review, 2023. https://doi.org/10.1007/s10462-023-10420-8
Published online 09.06.2025