Benchmarking and Survey of Explanation Methods for Black Box Models
This work addresses the need for transparency in AI for practitioners and researchers, but it is incremental as it primarily surveys and benchmarks existing methods.
The authors tackled the problem of explaining black-box AI models by categorizing existing explanation methods, presenting recent and widely used explainers, and providing visual and quantitative benchmarking comparisons.
The widespread adoption of black-box models in Artificial Intelligence has enhanced the need for explanation methods to reveal how these obscure models reach specific decisions. Retrieving explanations is fundamental to unveil possible biases and to resolve practical or ethical issues. Nowadays, the literature is full of methods with different explanations. We provide a categorization of explanation methods based on the type of explanation returned. We present the most recent and widely used explainers, and we show a visual comparison among explanations and a quantitative benchmarking.