A Survey on Methods and Metrics for the Assessment of Explainability under the Proposed AI Act

  title={A Survey on Methods and Metrics for the Assessment of Explainability under the Proposed AI Act},
  author={Francesco Sovrano and Salvatore Sapienza and Monica Palmirani and Fabio Vitali},
This study discusses the interplay between metrics used to measure the explainability of the AI systems and the proposed EU Artificial Intelligence Act. A standardisation process is ongoing: several entities (e.g. ISO) and scholars are discussing how to design systems that are compliant with the forthcoming Act and explainability metrics play a significant role. This study identifies the requirements that such a metric should possess to ease compliance with the AI Act. It does so according to… 

Tables from this paper


Metrics for Explainable AI: Challenges and Prospects
This paper discusses specific methods for evaluating the goodness of explanations, whether users are satisfied by explanations, how well users understand the AI systems, and how the human-XAI work system performs.
Evaluating the Quality of Machine Learning Explanations: A Survey on Methods and Metrics
A comprehensive overview of methods proposed in the current literature for the evaluation of ML explanations is presented, finding that the quantitative metrics for both model-based and example-based explanations are primarily used to evaluate the parsimony/simplicity of interpretability, and subjective measures have been embraced as the focal point for the human-centered evaluation of explainable systems.
Regulating Explainable AI in the European Union. An Overview of the Current Legal Framework(s)
Whether and to what extent individuals are, under EU law, entitled to a right to explanation of automated decision-making, especially when AI systems are used is explored.
A Survey of Methods for Explaining Black Box Models
A classification of the main problems addressed in the literature with respect to the notion of explanation and the type of black box system is provided to help the researcher to find the proposals more useful for his own work.
A comparative analysis of rule-based, model-agnostic methods for explainable artificial intelligence
This study proposes a novel comparative approach to evaluate and compare the rulesets produced by four post-hoc rule extractors by employing six quantitative metrics and demonstrates that these metrics can actually help identify superior methods over the others thus are capable of successfully modelling distinctively aspects of explainability.
On quantitative aspects of model interpretability
It is argued that the performance of methods along these dimensions can be orthogonally imputed to two conceptual parts, namely the feature extractor and the actual explainability method.
Why a Right to Explanation of Automated Decision-Making Does Not Exist in the General Data Protection Regulation
The problems show that the GDPR lacks precise language as well as explicit and well-defined rights and safeguards against automated decision-making, and therefore runs the risk of being toothless.
Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI
Previous efforts to define explainability in Machine Learning are summarized, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought, and a taxonomy of recent contributions related to the explainability of different Machine Learning models are proposed.
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
This survey provides an entry point for interested researchers and practitioners to learn key aspects of the young and rapidly growing body of research related to XAI, and review the existing approaches regarding the topic, discuss trends surrounding its sphere, and present major research trajectories.
Studies in the Logic of Explanation
To explain the phenomena in the world of our experience, to answer the question "why?" rather than only the question "what?", is one of the foremost objectives of all rational inquiry; and