Multi-Dimensional Model Integrity and Responsibility Assessment Index and Scoring Framework

2026-05-14

AI Summary

In high-stakes tabular data applications, relying solely on predictive performance is insufficient to comprehensively assess the trustworthiness of AI models, and existing evaluation approaches often treat key responsibility dimensions—such as interpretability, fairness, robustness, privacy, and sustainability—in isolation. This work proposes MIRAI, a unified evaluation framework that, for the first time, integrates these five responsibility dimensions into a standardized and comparable composite scoring system. By employing indicator fusion, directional alignment, and normalization techniques, MIRAI generates a single responsibility index under controlled conditions, enabling direct comparison across diverse model architectures and computational budgets. Empirical results demonstrate that certain simpler models achieve better multidimensional responsibility trade-offs than complex deep learning counterparts, and that predictive accuracy does not necessarily correlate with overall responsibility performance—providing empirical guidance for model selection under regulatory compliance requirements.

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.

Problem

• model integrity
• responsible AI
• tabular models
• evaluation framework
• multi-dimensional assessment

Innovation

• Model Integrity
• Responsibility Assessment
• Tabular AI
• Multi-Dimensional Evaluation
• MIRAI