The AI-DEC: A Card-based Design Method for User-centered AI Explanations
Not on the map. Why?
Abstract (arXiv)
Increasing evidence suggests that many deployed AI systems do not sufficiently support end-user interaction and information needs. Engaging end-users in the design of these systems can reveal user needs and expectations, yet effective ways of engaging end-users in the AI explanation design remain under-explored. To address this gap, we developed a design method, called AI-DEC, that defines four dimensions of AI explanations that are critical for the integration of AI systems -- communication content, modality, frequency, and direction -- and offers design examples for end-users to design AI explanations that meet their needs. We evaluated this method through co-design sessions with workers in healthcare, finance, and management industries who regularly use AI systems in their daily work. Findings indicate that the AI-DEC effectively supported workers in designing explanations that accommodated diverse levels of performance and autonomy needs, which varied depending on the AI system's workplace role and worker values. We discuss the implications of using the AI-DEC for the user-centered design of AI explanations in real-world systems.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 37 of its 152 references that are in the map. First posted on arXiv 26 May 2024.
Builds on
37 of 152 references.
References · 37
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
- 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
- 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,206
- 2020Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Makingcited by 281
- 2020Questioning the AI: Informing Design Practices for Explainable AI User Experiencescited by 253
- 2016Model-Agnostic Interpretability of Machine Learningcited by 219
- 2019One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniquescited by 164
- 2020Challenges in Deploying Machine Learning: a Survey of Case Studiescited by 152
- 2018Explaining Explanations in AIcited by 137
25 more
- 2020Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertaintycited by 129
- 2021Expanding Explainability: Towards Social Transparency in AI systemscited by 124
- 2021Human-Centered Explainable AI (XAI): From Algorithms to User Experiencescited by 123
- 2020Human-centered Explainable AI: Towards a Reflective Sociotechnical Approachcited by 90
- 2020Evaluating Saliency Map Explanations for Convolutional Neural Networks: A User Studycited by 86
- 2021Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applicationscited by 59
- 2022Designing for Responsible Trust in AI Systems: A Communication Perspectivecited by 48
- 2020Conceptual Metaphors Impact Perceptions of Human-AI Collaborationcited by 47
- 2022Investigating Explainability of Generative AI for Code through Scenario-based Designcited by 47
- 2023Understanding Frontline Workers' and Unhoused Individuals' Perspectives on AI Used in Homeless Servicescited by 29
- 2021Towards Relatable Explainable AI with the Perceptual Processcited by 27
- 2019How Case Based Reasoning Explained Neural Networks: An XAI Survey of Post-Hoc Explanation-by-Example in ANN-CBR Twinscited by 20
- 2021Towards A Process Model for Co-Creating AI Experiencescited by 18
- 2022Concept-based Explanations for Out-Of-Distribution Detectorscited by 16
- 2022Telling Stories from Computational Notebooks: AI-Assisted Presentation Slides Creation for Presenting Data Science Workcited by 15
- 2022Imagining new futures beyond predictive systems in child welfare: A qualitative study with impacted stakeholderscited by 15
- 2020Lessons Learned from Designing an AI-Enabled Diagnosis Tool for Pathologistscited by 9
- 2023Human-centered NLP Fact-checking: Co-Designing with Fact-checkers using Matchmaking for AIcited by 9
- 2022Subgoal-Based Explanations for Unreliable Intelligent Decision Support Systemscited by 6
- 2023Stakeholder-Centered AI Design: Co-Designing Worker Tools with Gig Workers through Data Probescited by 6
- 2022Polite or Direct? Conversation Design of a Smart Display for Older Adults Based on Politeness Theorycited by 4
- 2020Human-in-the-Loop Design Cycles -- A Process Framework that Integrates Design Sprints, Agile Processes, and Machine Learning with Humanscited by 3
- 2022The Unboxing Experience: Exploration and Design of Initial Interactions Between Children and Social Robotscited by 3
- 2024"It's Not a Replacement:" Enabling Parent-Robot Collaboration to Support In-Home Learning Experiences of Young Childrencited by 3
- 2023Investigating the Day-to-Day Experiences of Users with Traumatic Brain Injury with Conversational Agentscited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.