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

2021/02/15 by Markus Langer, Daniel Oster, Timo Speith +6 · 603 citations
Computer Science · Engineering · Medicine · Social Sciences · #Artificial Intelligence in Healthcare and Education #Artificial intelligence #Computer science #Economics #Engineering #Ethics and Social Impacts of AI #Explainable Artificial Intelligence (XAI) #Knowledge management #Management #Management science #Perspective (graphical) #Stakeholder #cs.AI #cs.HC

paper · pdf · open access · doi:10.1016/j.artint.2021.103473

published in Artificial Intelligence 296, 103473 (Elsevier BV) · 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

arxiv created 2021/02/15 · openalex publication_date 2021/02/15 · arxiv updated 2021/02/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

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.

Citations

• XPLAIN: a system for creating and explaining expert consulting programs

Cited by

• Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking
• Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods
• Do managers accept artificial intelligence? Insights into the role of business area and AI functionality
• A Graph-Theoretical Perspective on Law Design for Multiagent Systems
• Stop Saying "AI"
• Explainability Requirements as Hyperproperties
• Design Considerations for Human Oversight of AI: Insights from Co-Design Workshops and Work Design Theory
• Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations
• Visibility Allocation Systems: How Algorithmic Design Shapes Online Visibility and Societal Outcomes
• The Feature Understandability Scale for Human-Centred Explainable AI: Assessing Tabular Feature Importance
• Not All Explanations are Created Equal: Investigating the Pitfalls of Current XAI Evaluation
• Explaining explainable AI for healthcare: a Q-methodology study
• AI Error Difficulty Modulates the Effectiveness of Explainability in Decision Support Systems
• Explainability Needs in Agriculture: Exploring Dairy Farmers' User Personas
• Secure human oversight of AI: Threat modeling in a socio-technical context
• AI Harmonics: a human-centric and harms severity-adaptive AI risk assessment framework
• An Information-Flow Perspective on Explainability Requirements: Specification and Verification
• Six Guidelines for Trustworthy, Ethical and Responsible Automation Design
• Mental Models of Adversarial Machine Learning
• Enhancing the Interpretability of Rule-based Explanations through Information Retrieval
• Operationalizing Automated Essay Scoring: A Human-Aware Approach
• The Care Label Concept: A Certification Suite for Trustworthy and Resource-Aware Machine Learning
• The Metacognitive Demands and Opportunities of Generative AI
• Explainability in Context: A Multilevel Framework Aligning AI Explanations with Stakeholder with LLMs
• The Bidirectional Relationship Between XAI and Regulation: Operationalizing XAI for the AI Act
• A User Study Evaluating Argumentative Explanations in Diagnostic Decision Support
• From explanations to shared understandings of AI
• Disentangling AI Alignment: A Structured Taxonomy Beyond Safety and Ethics
• Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods
• Two Means to an End Goal: Connecting Explainability and Contestability in the Regulation of Public Sector AI
• Why is Regularization Underused? An Empirical Study on Trust and Adoption of Statistical Methods
• What Makes for a Good Saliency Map? Comparing Strategies for Evaluating Saliency Maps in Explainable AI (XAI)
• On the Need to Rethink Trust in AI Assistants for Software Development: A Critical Review
• In Terms of Explainability: Refining Requirements for Self-Explainable Systems
• Artificial intelligence explainability: the technical and ethical dimensions. [europepmc]
• Deep Cross-Corpus Speech Emotion Recognition: Recent Advances and Perspectives. [europepmc]
• An exploration of expectations and perceptions of practicing physicians on the implementation of computerized clinical decision support systems using a Qsort approach. [europepmc]
• Measuring the Usability and Quality of Explanations of a Machine Learning Web-Based Tool for Oral Tongue Cancer Prognostication. [europepmc]
• Explainable artificial intelligence (XAI) detects wildfire occurrence in the Mediterranean countries of Southern Europe. [europepmc]
• Yes we care!-Certification for machine learning methods through the care label framework. [europepmc]
• ETECADx: Ensemble Self-Attention Transformer Encoder for Breast Cancer Diagnosis Using Full-Field Digital X-ray Breast Images. [europepmc]
• Explainable AI as evidence of fair decisions. [europepmc]
• Essential properties and explanation effectiveness of explainable artificial intelligence in healthcare: A systematic review. [europepmc]
• Explainability of deep learning models in medical video analysis: a survey. [europepmc]
• The slow-paced digital evolution of pathology: lights and shadows from a multifaceted board. [europepmc]
• What is critical for human-centered AI at work? - Toward an interdisciplinary theory. [europepmc]
• Using test-time augmentation to investigate explainable AI: inconsistencies between method, model and human intuition. [europepmc]
• Expectation management in AI: A framework for understanding stakeholder trust and acceptance of artificial intelligence systems. [europepmc]
• Explainability does not mitigate the negative impact of incorrect AI advice in a personnel selection task. [europepmc]
• Identification of avoidable patients at triage in a Paediatric Emergency Department: a decision support system using predictive analytics. [europepmc]
• Stakeholder-centric explanations for black-box decisions: an XAI process model and its application to automotive goodwill assessments. [europepmc]
• Influence of Explanatory Variable Distributions on the Behavior of the Impurity Measures Used in Classification Tree Learning. [europepmc]
• Exploring the Unseen: A Survey of Multi-Sensor Fusion and the Role of Explainable AI (XAI) in Autonomous Vehicles. [europepmc]
• Making sense of transformer success. [europepmc]
• Decision factors for the selection of AI-based decision support systems-The case of task delegation in prognostics. [europepmc]
• Explainable AI in medicine: challenges of integrating XAI into the future clinical routine. [europepmc]
• Designing effective explainable AI: a human-centered evaluation of explanation formats in financial decision-making. [europepmc]
• A Study on the Robustness and Stability of Explainable Deep Learning in an Imbalanced Setting: The Exploration of the Conformational Space of G Protein-Coupled Receptors [europepmc]
• Predicting skin cancer risk from facial images with an explainable artificial intelligence (XAI) based approach: a proof-of-concept study [europepmc]

Related

• Reviewing the Need for Explainable Artificial Intelligence (xAI)
• Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI
• A multi-component framework for the analysis and design of explainable artificial intelligence
• A Means-End Account of Explainable Artificial Intelligence
• Explainable AI (XAI): A systematic meta-survey of current challenges and future opportunities