Notions of explainability and evaluation approaches for explainable artificial intelligence

By Giulia Vilone, Longo Luca. Information Fusion, 2021

525 citations recorded by the source corpus.

Abstract Explainable Artificial Intelligence (XAI) has experienced a significant growth over the last few years. This is due to the widespread application of machine learning, particularly deep learning, that has led to the development of highly accurate models that lack explainability and interpretability. A plethora of methods to tackle this problem have been proposed, developed and tested, coupled with several studies attempting to define the concept of explainability and its evaluation. This systematic review contributes to the body of knowledge by clustering all the scientific studies via a hierarchical system that classifies theories and notions related to the concept of explainability and the evaluation approaches for XAI methods. The structure of this hierarchy builds on top of an exhaustive analysis of existing taxonomies and peer-reviewed scientific material. Findings suggest that scholars have identified numerous notions and requirements that an explanation should meet in order to be easily understandable by end-users and to provide actionable information that can inform decision making. They have also suggested various approaches to assess to what degree machine-generated explanations meet these demands. Overall, these approaches can be clustered into human-centred evaluations and evaluations with more objective metrics. However, despite the vast body of knowledge developed around the concept of explainability, there is not a general consensus among scholars on how an explanation should be defined, and how its validity and reliability assessed. Eventually, this review concludes by critically discussing these gaps and limitations, and it defines future research directions with explainability as the starting component of any artificial intelligent system.

Subfields: Artificial Intelligence, Health Informatics

View Paper: https://www.semanticscholar.org/paper/f10ce6ea0b54fc0a71eff8ae4e3d1840f19c4517

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Health Informatics

Citations in the corpus

Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation (2023, background): “Natural language explanations [67, 27], quantitative measures of the quality of explanations [68, 69], and models that support their learning process with formal symbolic basis such as language, rules, compositional relationships or knowledge graphs (neural-symbolic learning and reasoning [66]) are ”
From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI (2022, background): “Closest related to our work is the survey of Zhou et al. [306] that presents a concise overview and discussion regarding evaluating XAI without a structured literature review, and the work of Vilone and Longo [258] that present a list of concepts related to explainability and discuss evaluation meth”
Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions (2023, background): “Similarly, Vilone and Longo [27] aggregate evaluation approaches for XAI methods from several scientific studies via a hierarchical system.”
Deterministic Local Interpretable Model-Agnostic Explanations for Stable Explainability (2021, unknown): “Vilone et al. and Alvarez-Melis et al. [7,8] deﬁned stability as the consistency of similar explanations for the same or similar inputs.”