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

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.

References in corpus (8)

• Distilling the Knowledge in a Neural Network
• Towards A Rigorous Science of Interpretable Machine Learning
• Understanding Neural Networks Through Deep Visualization
• Deep Learning: A Critical Appraisal
• What Does Explainable AI Really Mean? A New Conceptualization of Perspectives
• Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks
• On the Robustness of Most Probable Explanations
• Explaining Classification Models Built on High-Dimensional Sparse Data

Cited by in corpus (4)

• Explaining AI as an Exploratory Process: The Peircean Abduction Model
• From Shallow to Deep Interactions Between Knowledge Representation, Reasoning and Machine Learning (Kay R. Amel group)
• Play MNIST For Me! User Studies on the Effects of Post-Hoc, Example-Based Explanations & Error Rates on Debugging a Deep Learning, Black-Box Classifier
• A Causal Lens for Peeking into Black Box Predictive Models: Predictive Model Interpretation via Causal Attribution