Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI

TL;DR

This literature review synthesizes key ideas, historical context, and psychological theories related to explanations in AI systems, highlighting challenges and suggesting detailed reporting standards for explainable AI research.

Contribution

It provides a comprehensive meta-review of explainability in AI, integrating historical, psychological, and methodological perspectives, and recommends improved empirical reporting practices.

Findings

Key concepts and issues in AI explainability are summarized.

Historical evolution of explanation systems in AI is outlined.

Recommendations for detailed empirical reporting in XAI research are provided.

Abstract

This is an integrative review that address the question, "What makes for a good explanation?" with reference to AI systems. Pertinent literatures are vast. Thus, this review is necessarily selective. That said, most of the key concepts and issues are expressed in this Report. The Report encapsulates the history of computer science efforts to create systems that explain and instruct (intelligent tutoring systems and expert systems). The Report expresses the explainability issues and challenges in modern AI, and presents capsule views of the leading psychological theories of explanation. Certain articles stand out by virtue of their particular relevance to XAI, and their methods, results, and key points are highlighted. It is recommended that AI/XAI researchers be encouraged to include in their research reports fuller details on their empirical or experimental methods, in the fashion of experimental psychology research reports: details on Participants, Instructions, Procedures, Tasks, Dependent Variables (operational definitions of the measures and metrics), Independent Variables (conditions), and Control Conditions.