Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI

TL;DR

Explainable Artificial Intelligence addresses the need to reconcile high-performance AI with human-centered explanations. The authors propose audience-focused definitions and two complementary taxonomies: one for transparent and post-hoc explainability across traditional ML models and a second DL-specific taxonomy, augmented by discussions of hybrid approaches. They connect XAI with Responsible AI, fairness, privacy, and data fusion, and outline practical challenges such as metric standardization and security implications. The work ultimately advocates for principled, governance-driven deployment of explainable AI in real organizations, emphasizing both methodological advances and organizational guidelines.

Abstract

In the last years, Artificial Intelligence (AI) has achieved a notable momentum that may deliver the best of expectations over many application sectors across the field. For this to occur, the entire community stands in front of the barrier of explainability, an inherent problem of AI techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI. Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is acknowledged as a crucial feature for the practical deployment of AI models. This overview examines the existing literature in the field of XAI, including a prospect toward what is yet to be reached. We summarize previous efforts to define explainability in Machine Learning, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought. We then propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at Deep Learning methods for which a second taxonomy is built. This literature analysis serves as the background for a series of challenges faced by XAI, such as the crossroads between data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to XAI with a reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.

Figures (14)

• Figure 1: Evolution of the number of total publications whose title, abstract and/or keywords refer to the field of XAI during the last years. Data retrieved from Scopus®(December 10th, 2019) by using the search terms indicated in the legend when querying this database. It is interesting to note the latent need for interpretable AI models over time (which conforms to intuition, as interpretability is a requirement in many scenarios), yet it has not been until 2017 when the interest in techniques to explain AI models has permeated throughout the research community.
• Figure 2: Diagram showing the different purposes of explainability in ML models sought by different audience profiles. Two goals occur to prevail across them: need for model understanding, and regulatory compliance. Image partly inspired by the one presented in ibm2019, used with permission from IBM.
• Figure 3: Conceptual diagram exemplifying the different levels of transparency characterizing a ML model $M_{\bm{\varphi}}$, with $\bm{\varphi}$ denoting the parameter set of the model at hand: (a) simulatability; (b) decomposability; (c) algorithmic transparency. Without loss of generality, the example focuses on the ML model as the explanation target. However, other targets for explainability may include a given example, the output classes or the dataset itself.
• Figure 4: Conceptual diagram showing the different post-hoc explainability approaches available for a ML model $M_{\bm{\varphi}}$.
• Figure 5: Graphical illustration of the levels of transparency of different ML models considered in this overview: (a) Linear regression; (b) Decision trees; (c) K-Nearest Neighbors; (d) Rule-based Learners; (e) Generalized Additive Models; (f) Bayesian Models.