Volume 11 • Issue 2 • PP: 22–32 • 2026
Explaining AI Decisions to Mitigate Cognitive Biases in Human-AI Collaboration
View PDF Abstract
Human-AI collaboration can improve decision quality only when users know when to rely on an AI recommendation and when to resist it. Explanations are often proposed as a remedy, but explanation content can also intensify automation bias or reinforce a user’s initial belief. This paper presents a cognitive explanation selection model for mitigating over-reliance and under-reliance in AI-assisted decision tasks. The study compares no explanation, feature-based, contrastive, example-driven, and hybrid explanations across simulated novice, intermediate, and expert decision makers using a public medical decision dataset as the task substrate. The analysis focuses on reliance behaviour rather than on model accuracy alone. The proposed model estimates when the user is likely to accept a wrong recommendation, reject a correct recommendation, or accept advice simply because it confirms an initial judgment. The results indicate that contrastive and hybrid explanations are more effective for reducing automation bias, while example-driven explanations preserve trust for lower-expertise users. The paper concludes with a transparent interface loop for high-stakes environments in which explanation style is selected according to user expertise, AI confidence, and human-AI agreement.
Keywords
References
[1] H. Vasconcelos, M. Jorke, M. Grunde-McLaughlin, T. Gerstenberg, M. S. Bernstein, and R. Krishna, “Explanations can reduce overreliance on AI systems during decision-making,” Proceedings of the ACM on Human- Computer Interaction, vol. 7, CSCW1, pp. 1–38, 2023.
[2] M. Vered, P. Howe, T. Miller, L. Sonenberg, and E. Velloso, “The effects of explanations on automation bias,” Artificial Intelligence, vol. 322, article 103952, 2023.
[3] N. Scharowski, S. A. C. Perrig, M. Svab, K. Opwis, and F. Bruhlmann, “Exploring the effects of human-centered AI explanations on trust and reliance,” Frontiers in Computer Science, vol. 5, article 1151150, 2023.
[4] J. Schoeffer, M. De-Arteaga, and N. Kuehl, “Explanations, fairness, and appropriate reliance in human-AI decision-making,” in Proceedings of the CHI Conference on Human Factors in Computing Systems, 2024.
[5] Z. Bucinca, S. Swaroop, A. E. Paluch, F. Doshi-Velez, and K. Z. Gajos, “Contrastive explanations that anticipate human misconceptions can improve human decision-making skills,” in Proceedings of the CHI Conference on Human Factors in Computing Systems, 2025.
[6] Y. Li, B. Wu, Y. Huang, and S. Luan, “Developing trustworthy artificial intelligence: Insights from research on interpersonal, human-automation, and human-AI trust,” Frontiers in Psychology, vol. 15, article 1382693, 2024.
[7] A. Bashkirova and D. Krpan, “Confirmation bias in AIassisted decision-making: AI triage recommendations congruent with expert judgments increase psychologist trust and recommendation acceptance,” Computers in Human Behavior: Artificial Humans, vol. 2, no. 1, article 100066, 2024.
[8] O. Lammert, C. Holzmeister, and colleagues, “Humans in XAI: Increased reliance in decision-making under uncertainty,” Frontiers in Behavioral Economics, vol. 3, article 1377075, 2024.
[9] F. H. Chaleshtori, M. T. Ribeiro, and colleagues, “On evaluating explanation utility for human-AI decision making,” in Findings of the Association for Computational Linguistics: EMNLP 2024, 2024.
[10] G. Romeo, L. Conti, and colleagues, “Exploring automation bias in human-AI collaboration: A review and implications for explainable AI,” AI & Society, 2025.
[11] B. M. Henrique, H. Sobreiro, and colleagues, “Trust in artificial intelligence: Literature review and main path analysis,” Computers in Human Behavior: Artificial Humans, vol. 2, no. 1, article 100043, 2024.
[12] S. Blanco, “Human trust in AI: A relationship beyond reliance,” AI and Ethics, 2025.
[13] W. H. Wolberg, W. N. Street, and O. L. Mangasarian, “Breast cancer Wisconsin diagnostic dataset,” UCI Machine Learning Repository, 1995.
Cite This Article
Choose your preferred format