MQG4AI Towards Responsible High-risk AI - Illustrated for Transparency Focusing on Explainability Techniques

2025-02-17

AI Summary

To address insufficient transparency during model explanation and the challenge of sustaining ethical and regulatory compliance in high-risk AI systems, this paper proposes MQG4AI—a quality management system tailored to the AI lifecycle. Centered on configurable Quality Gates, MQG4AI dynamically integrates technical implementation, ethical principles, and regulatory requirements, and innovatively embeds an Explanation Quality Assessment Guideline into lifecycle planning. It achieves structured assurance of explainability and transparency through AI lifecycle modeling, cross-phase information linkage mechanisms, and integration of a Responsible AI Knowledge Graph. The core contribution is the first responsible Quality Gate framework explicitly designed to accommodate AI’s evolutionary nature—providing developers of high-risk AI systems with an actionable, verifiable, and sustainably aligned compliance methodology.

Technology Category

• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Knowledge Representation and Reasoning: Qualitative Reasoning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

As artificial intelligence (AI) systems become increasingly integrated into critical domains, ensuring their responsible design and continuous development is imperative. Effective AI quality management (QM) requires tools and methodologies that address the complexities of the AI lifecycle. In this paper, we propose an approach for AI lifecycle planning that bridges the gap between generic guidelines and use case-specific requirements (MQG4AI). Our work aims to contribute to the development of practical tools for implementing Responsible AI (RAI) by aligning lifecycle planning with technical, ethical and regulatory demands. Central to our approach is the introduction of a flexible and customizable Methodology based on Quality Gates, whose building blocks incorporate RAI knowledge through information linking along the AI lifecycle in a continuous manner, addressing AIs evolutionary character. For our present contribution, we put a particular emphasis on the Explanation stage during model development, and illustrate how to align a guideline to evaluate the quality of explanations with MQG4AI, contributing to overall Transparency.

Problem

• Responsible AI lifecycle planning
• Quality Gates methodology
• Transparency in explainability techniques

Innovation

• Quality Gates Methodology
• AI lifecycle planning
• Explanation stage alignment