Three Levels of AI Transparency

2023/02/01 by Kashyap Haresamudram, Stefan Larsson, Fredrik Heintz · 3 citations
Social Sciences · Computer Science · #Ethics and Social Impacts of AI #Explainable Artificial Intelligence (XAI) #Adversarial Robustness in Machine Learning

paper · doi:10.1109/mc.2022.3213181

Abstract

The concept of transparency is fragmented in artificial intelligence (AI) research, often limited to transparency of the algorithm alone. We propose that AI transparency operates on three levels—algorithmic, interaction, and social—all of which need to be considered to build trust in AI. We expand upon these levels using current research directions, and identify research gaps resulting from the conceptual fragmentation of AI transparency highlighted within the context of the three levels.

Cited by

• Reimagining the Philosophy of Experimentation in Chemistry Education: Embracing AI as a Tool for Scientific Inquiry
• Exploring factors influencing user perspective of ChatGPT as a technology that assists in healthcare decision making: A cross sectional survey study. [europepmc]
• Responsibility Gap(s) Due to the Introduction of AI in Healthcare: An Ubuntu-Inspired Approach. [europepmc]

Related

• Users are the North Star for AI Transparency
• AI data transparency: an exploration through the lens of AI incidents
• Through the Looking-Glass: Transparency Implications and Challenges in Enterprise AI Knowledge Systems
• Stabilizing translucencies: Governing AI transparency by standardization
• Making Transparency Advocates: An Educational Approach Towards Better Algorithmic Transparency in Practice