An Empirical Survey on Explainable AI Technologies: Recent Trends, Use-Cases, and Categories from Technical and Application Perspectives

Abstract

In a wide range of industries and academic fields, artificial intelligence is becoming increasingly prevalent. AI models are taking on more crucial decision-making tasks as they grow in popularity and performance. Although AI models, particularly machine learning models, are successful in research, they have numerous limitations and drawbacks in practice. Furthermore, due to the lack of transparency behind their behavior, users need more understanding of how these models make specific decisions, especially in complex state-of-the-art machine learning algorithms. Complex machine learning systems utilize less transparent algorithms, thereby exacerbating the problem. This survey analyzes the significance and evolution of explainable AI (XAI) research across various domains and applications. Throughout this study, a rich repository of explainability classifications and summaries has been developed, along with their applications and practical use cases. We believe this study will make it easier for researchers to understand all explainability methods and access their applications simultaneously.

Exploring the Black Box: Analyzing Explainable AI Challenges and Best Practices Through Stack Exchange Discussions

“…Figure 15 also reveals that despite the efforts of several studies (Nagahisarchoghaei et al, 2023;Das and Rad, 2020;Angelov et al, 2021) to clarify various definitions of XAI for users, questions about comparing and distinguishing these definitions persist, even though XAI is popular. This presents an opportunity for research to articulate these definitions more practically.…”

“…This presents an opportunity for research to articulate these definitions more practically. Prior research (Nagahisarchoghaei et al, 2023) has identified the applications of XAI technologies. The primary application of these technologies is to enhance AI system transparency for more practical reliability (Hanif et al, 2023).…”