What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research

Abstract

Previous research in Explainable Artificial Intelligence (XAI) suggests that a main aim of explainability approaches is to satisfy specific interests, goals, expectations, needs, and demands regarding artificial systems (we call these stakeholders' desiderata) in a variety of contexts. However, the literature on XAI is vast, spreads out across multiple largely disconnected disciplines, and it often remains unclear how explainability approaches are supposed to achieve the goal of satisfying stakeholders' desiderata. This paper discusses the main classes of stakeholders calling for explainability of artificial systems and reviews their desiderata. We provide a model that explicitly spells out the main concepts and relations necessary to consider and investigate when evaluating, adjusting, choosing, and developing explainability approaches that aim to satisfy stakeholders' desiderata. This model can serve researchers from the variety of different disciplines involved in XAI as a common ground. It emphasizes where there is interdisciplinary potential in the evaluation and the development of explainability approaches.

57 pages, 2 figures, 1 table, to be published in Artificial Intelligence, Markus Langer, Daniel Oster and Timo Speith share first-authorship of this paper

References in corpus (28)

• Towards A Rigorous Science of Interpretable Machine Learning
• Semantics derived automatically from language corpora contain human-like biases
• Methods for Interpreting and Understanding Deep Neural Networks
• European Union regulations on algorithmic decision-making and a "right to explanation"
• The social dilemma of autonomous vehicles
• Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
• Explaining Explanations in AI
• 'It's Reducing a Human Being to a Percentage'; Perceptions of Justice in Algorithmic Decisions
• Beyond Product Quantization: Deep Progressive Quantization for Image Retrieval
• Deep Recurrent Quantization for Generating Sequential Binary Codes
• A systematic review and taxonomy of explanations in decision support and recommender systems
• What Does Explainable AI Really Mean? A New Conceptualization of Perspectives
• One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
• Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approaches
• The Pragmatic Turn in Explainable Artificial Intelligence (XAI)
• Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI
• Metrics for Explainable AI: Challenges and Prospects
• Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciences
• One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparency
• The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification
• Explainable Planning
• Stakeholders in Explainable AI
• Defining Explainable AI for Requirements Analysis
• Counterfactual States for Atari Agents via Generative Deep Learning
• Explaining Explanations to Society
• Abstraction for Zooming-In to Unsolvability Reasons of Grid-Cell Problems
• A New Approach for Explainable Multiple Organ Annotation with Few Data
• Local Score Dependent Model Explanation for Time Dependent Covariates

Cited by in corpus (55)

• Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions
• A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts
• The Metacognitive Demands and Opportunities of Generative AI
• Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction
• "Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interaction
• Explainable Artificial Intelligence: Precepts, Methods, and Opportunities for Research in Construction
• Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review
• AI, Opacity, and Personal Autonomy
• Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contexts
• XAIR: A Framework of Explainable AI in Augmented Reality
• On the Quest for Effectiveness in Human Oversight: Interdisciplinary Perspectives
• Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making
• "There Is Not Enough Information": On the Effects of Explanations on Perceptions of Informational Fairness and Trustworthiness in Automated Decision-Making
• The Conflict Between Explainable and Accountable Decision-Making Algorithms
• Certification Labels for Trustworthy AI: Insights From an Empirical Mixed-Method Study
• A Critical Survey on Fairness Benefits of Explainable AI
• Directive Explanations for Monitoring the Risk of Diabetes Onset: Introducing Directive Data-Centric Explanations and Combinations to Support What-If Explorations
• Is Conversational XAI All You Need? Human-AI Decision Making With a Conversational XAI Assistant
• Bridging the Transparency Gap: What Can Explainable AI Learn From the AI Act?
• Blaming Humans and Machines: What Shapes People's Reactions to Algorithmic Harm
• FATE in AI: Towards Algorithmic Inclusivity and Accessibility
• Appropriate Fairness Perceptions? On the Effectiveness of Explanations in Enabling People to Assess the Fairness of Automated Decision Systems
• Explainability Auditing for Intelligent Systems: A Rationale for Multi-Disciplinary Perspectives
• Whither Bias Goes, I Will Go: An Integrative, Systematic Review of Algorithmic Bias Mitigation
• Current and future roles of artificial intelligence in retinopathy of prematurity
• Path-based Explanation for Knowledge Graph Completion
• Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models
• What Does Evaluation of Explainable Artificial Intelligence Actually Tell Us? A Case for Compositional and Contextual Validation of XAI Building Blocks
• How Can We Develop Explainable Systems? Insights from a Literature Review and an Interview Study
• Towards a Comprehensive Human-Centred Evaluation Framework for Explainable AI
• Yes We Care! -- Certification for Machine Learning Methods through the Care Label Framework
• Explanation as a process: user-centric construction of multi-level and multi-modal explanations
• Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking
• The Impact of Explanations on Fairness in Human-AI Decision-Making: Protected vs Proxy Features
• Information That Matters: Exploring Information Needs of People Affected by Algorithmic Decisions
• A Human-Centric Perspective on Fairness and Transparency in Algorithmic Decision-Making
• A Comprehensive Survey on Self-Interpretable Neural Networks
• XAI in Automated Fact-Checking? The Benefits Are Modest and There's No One-Explanation-Fits-All
• Identifying Explanation Needs of End-users: Applying and Extending the XAI Question Bank
• Opacity as a Feature, Not a Flaw: The LoBOX Governance Ethic for Role-Sensitive Explainability and Institutional Trust in AI
• A three-Level Framework for LLM-Enhanced eXplainable AI: From technical explanations to natural language
• Generative Perturbation Analysis for Probabilistic Black-Box Anomaly Attribution
• Design Considerations for Human Oversight of AI: Insights from Co-Design Workshops and Work Design Theory
• Give Me a Choice: The Consequences of Restricting Choices Through AI-Support for Perceived Autonomy, Motivational Variables, and Decision Performance
• The Role of Accuracy and Validation Effectiveness in Conversational Business Analytics
• The Importance of Distrust in AI
• Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations
• Better Together? The Role of Explanations in Supporting Novices in Individual and Collective Deliberations about AI
• The Care Label Concept: A Certification Suite for Trustworthy and Resource-Aware Machine Learning
• Not All Explanations are Created Equal: Investigating the Pitfalls of Current XAI Evaluation
• Explainability Requirements as Hyperproperties
• Explanatory Pluralism in Explainable AI
• Against Explainable Artificial Intelligence In Law: Why Justifiable Ai Matters. A Credit Scoring Example
• MAIR: Framework for mining relationships between research articles, strategies, and regulations in the field of explainable artificial intelligence
• Mental Models of Adversarial Machine Learning