Abstract:Artificial intelligence in high-stakes tabular domains cannot be evaluated by predictive performance alone, yet current practice still assesses explainability, fairness, robustness, privacy, and sustainability mostly in isolation. We propose the Model Integrity and Responsibility Assessment Index (MIRAI), a unified evaluation framework that measures tabular models across these five dimensions under a controlled comparison setting and aggregates them into a single score. MIRAI combines established metrics through normalized and direction-aligned dimension scores, which enables direct comparison across models with different architectural and computational profiles. Experiments on healthcare, financial, and socioeconomic datasets show that higher predictive performance does not necessarily imply better overall integrity and responsibility. In several cases, simpler models achieve a stronger cross-dimensional balance than more complex deep tabular architectures. MIRAI provides a compact and practical basis for responsible model selection in regulated settings.
| Comments: | Accepted to the 39th Canadian Conference on Artificial Intelligence (Canadian AI 2026) |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.14550 [cs.LG] |
| (or arXiv:2605.14550v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.14550 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Phuc Truong Loc Nguyen [view email]
[v1]
Thu, 14 May 2026 08:29:36 UTC (53 KB)