Stakeholders in Explainable AI

Abstract

There is general consensus that it is important for artificial intelligence (AI) and machine learning systems to be explainable and/or interpretable. However, there is no general consensus over what is meant by 'explainable' and 'interpretable'. In this paper, we argue that this lack of consensus is due to there being several distinct stakeholder communities. We note that, while the concerns of the individual communities are broadly compatible, they are not identical, which gives rise to different intents and requirements for explainability/interpretability. We use the software engineering distinction between validation and verification, and the epistemological distinctions between knowns/unknowns, to tease apart the concerns of the stakeholder communities and highlight the areas where their foci overlap or diverge. It is not the purpose of the authors of this paper to 'take sides' - we count ourselves as members, to varying degrees, of multiple communities - but rather to help disambiguate what stakeholders mean when they ask 'Why?' of an AI.

arXiv commentPresented at AAAI FSS-18: Artificial Intelligence in Government and Public Sector, Arlington, Virginia, USA

References in corpus (10)

• Axiomatic Attribution for Deep Networks
• European Union regulations on algorithmic decision-making and a "right to explanation"
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
• The (Un)reliability of saliency methods
• An unexpected unity among methods for interpreting model predictions
• Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systems
• Generating Visual Explanations
• Sufficient Conditions for Idealised Models to Have No Adversarial Examples: a Theoretical and Empirical Study with Bayesian Neural Networks
• Influence-Directed Explanations for Deep Convolutional Networks

Cited by in corpus (16)

• Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges
• What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research
• Explainable Artificial Intelligence for Process Mining: A General Overview and Application of a Novel Local Explanation Approach for Predictive Process Monitoring
• Explainable Artificial Intelligence (XAI): An Engineering Perspective
• Towards Explainable Neural-Symbolic Visual Reasoning
• A framework for fostering transparency in shared artificial intelligence models by increasing visibility of contributions
• Human-Centered Explainable AI (XAI): From Algorithms to User Experiences
• Local Post-Hoc Explanations for Predictive Process Monitoring in Manufacturing
• Unexplainability and Incomprehensibility of Artificial Intelligence
• Explainable Goal-Driven Agents and Robots -- A Comprehensive Review
• Explainable AI for Intelligence Augmentation in Multi-Domain Operations
• Towards an Explanation Space to Align Humans and Explainable-AI Teamwork
• Quantifying Transparency of Machine Learning Systems through Analysis of Contributions
• Teaching Solid Mechanics to Artificial Intelligence: a fast solver for heterogeneous solids
• Interpretable collaborative data analysis on distributed data
• Human-Imitating Metrics for Training and Evaluating Privacy Preserving Emotion Recognition Models Using Sociolinguistic Knowledge