Measuring the Quality of Explanations: The System Causability Scale (SCS)

By Andreas Holzinger, André M. Carrington, Heimo Müller. KI - Künstliche Intelligenz, 2019

385 citations recorded by the source corpus.

Recent success in Artificial Intelligence (AI) and Machine Learning (ML) allow problem solving automatically without any human intervention. Autonomous approaches can be very convenient. However, in certain domains, e.g., in the medical domain, it is necessary to enable a domain expert to understand, why an algorithm came up with a certain result. Consequently, the field of Explainable AI (xAI) rapidly gained interest worldwide in various domains, particularly in medicine. Explainable AI studies transparency and traceability of opaque AI/ML and there are already a huge variety of methods. For example with layer-wise relevance propagation relevant parts of inputs to, and representations in, a neural network which caused a result, can be highlighted. This is a first important step to ensure that end users, e.g., medical professionals, assume responsibility for decision making with AI/ML and of interest to professionals and regulators. Interactive ML adds the component of human expertise to AI/ML processes by enabling them to re-enact and retrace AI/ML results, e.g. let them check it for plausibility. This requires new human–AI interfaces for explainable AI. In order to build effective and efficient interactive human–AI interfaces we have to deal with the question of how to evaluate the quality of explanations given by an explainable AI system. In this paper we introduce our System Causability Scale to measure the quality of explanations. It is based on our notion of Causability (Holzinger et al. in Wiley Interdiscip Rev Data Min Knowl Discov 9(4), 2019) combined with concepts adapted from a widely-accepted usability scale.

Subfields: Artificial Intelligence, Health Informatics

View Paper: https://www.semanticscholar.org/paper/56760db66eb98d271d8b3b8e3e6af28eab1959ea

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

Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence (2023, methodology): “Holzinger et al. [163] devised a notion of causability, which they later combined with a widely-accepted usability scale to form the System Causability Scale (SCS).”
Cross-Loss Influence Functions to Explain Deep Network Representations (2020, background): “…have been proposed, including interpretable neural network approaches (Wang et al., 2016), natural language generation of explanations (Mullenbach et al., 2018; Wiegreﬀe and Pinter, 2019; Chen et al., 2021), and many others Hoﬀman et al. (2018); Holzinger et al. (2020); Linardatos et al. (2021).”
A historical perspective of explainable Artificial Intelligence (2020, background): “…possible for explanations of human statements, as the explanation is per-se related to a human model, measuring the causal understanding of an explanation of a machine statement has to be based on a causal model, which is not the case for most machine learning algorithms (Holzinger et al., 2020).”
Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation (2023, methodology): “Examples include the System Causability Scale [123] or the Muir Trust Scale [124], which are widely adopted in human robot interaction and robotics and rely on predictability (To what extent the robot behavior [the output of the AI-based system] can be predicted from moment to moment?)”