A Measure of Explanatory Effectiveness
In most conversations about explanation and AI, the recipient of the explanation (the explainee) is suspiciously absent, despite the problem being ultimately communicative in nature. We pose the problem `explaining AI systems' in terms of a two-player cooperative game in which each agent seeks to maximise our proposed measure of explanatory effectiveness. This measure serves as a foundation for the automated assessment of explanations, in terms of the effects that any given action in the game has on the internal state of the explainee.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Generating Skyline Explanations for Graph Neural Networks
This paper proposes a novel approach to generate subgraph explanations for graph neural networks GNNs that simultaneously optimize multiple measures for explainability. Existing GNN explanation methods often compute subg…
Explanation GenerationImproved Explanatory Efficacy on Human Affect and Workload through Interactive Process in Artificial Intelligence
Despite recent advances in the field of explainable artificial intelligence systems, a concrete quantitative measure for evaluating the usability of such systems is nonexistent. Ensuring the success of an explanatory int…
EEGElectroencephalogram (EEG)Explainable artificial intelligenceRecommendation SystemsA Framework for Using Value-Added in Regressions
As increasingly popular metrics of worker and institutional quality, estimated value-added (VA) measures are now widely used as dependent or explanatory variables in regressions. For example, VA is used as an explanatory…
Convex Fairness Constrained Model Using Causal Effect Estimators
Recent years have seen much research on fairness in machine learning. Here, mean difference (MD) or demographic parity is one of the most popular measures of fairness. However, MD quantifies not only discrimination but a…
Binary ClassificationFairnessmodelregressionHow Far Can Sharpness and Complexity Jointly Explain Generalization?
Sharpness and complexity are two central factors in the generalization analysis of deep neural networks. Existing quantitative evaluations of generalization measures have largely focused on individual scalar measures, le…