Foundations of Explainable Knowledge-Enabled Systems
This work addresses the need for explainable AI in critical settings for end-users and decision-makers, but it is incremental as it builds on past approaches.
The paper provides a historical overview of explainable AI systems, focusing on knowledge-enabled systems across domains like expert systems and machine learning, and proposes new definitions for explanations and explainable systems to address user- and context-focused needs.
Explainability has been an important goal since the early days of Artificial Intelligence. Several approaches for producing explanations have been developed. However, many of these approaches were tightly coupled with the capabilities of the artificial intelligence systems at the time. With the proliferation of AI-enabled systems in sometimes critical settings, there is a need for them to be explainable to end-users and decision-makers. We present a historical overview of explainable artificial intelligence systems, with a focus on knowledge-enabled systems, spanning the expert systems, cognitive assistants, semantic applications, and machine learning domains. Additionally, borrowing from the strengths of past approaches and identifying gaps needed to make explanations user- and context-focused, we propose new definitions for explanations and explainable knowledge-enabled systems.