mlsanityData to 7 Oct 2026

Towards an Explanation Space to Align Humans and Explainable-AI Teamwork

arXiv 2106.01503 ↗First posted 2 Jun 2021cs.AI cs.HCcited by 0

Not on the map. Why?

Abstract (arXiv)

Providing meaningful and actionable explanations to end-users is a fundamental prerequisite for implementing explainable intelligent systems in the real world. Explainability is a situated interaction between a user and the AI system rather than being static design principles. The content of explanations is context-dependent and must be defined by evidence about the user and its context. This paper seeks to operationalize this concept by proposing a formative architecture that defines the explanation space from a user-inspired perspective. The architecture comprises five intertwined components to outline explanation requirements for a task: (1) the end-users mental models, (2) the end-users cognitive process, (3) the user interface, (4) the human-explainer agent, and the (5) agent process. We first define each component of the architecture. Then we present the Abstracted Explanation Space, a modeling tool that aggregates the architecture's components to support designers in systematically aligning explanations with the end-users work practices, needs, and goals. It guides the specifications of what needs to be explained (content - end-users mental model), why this explanation is necessary (context - end-users cognitive process), to delimit how to explain it (format - human-explainer agent and user interface), and when should the explanations be given. We then exemplify the tool's use in an ongoing case study in the aircraft maintenance domain. Finally, we discuss possible contributions of the tool, known limitations/areas for improvement, and future work to be done.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 82 references that are in the map. First posted on arXiv 2 Jun 2021.

Builds on

17 of 82 references.

References · 17

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  4. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  5. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 359
  6. 2018Metrics for Explainable AI: Challenges and Prospectscited by 257
  7. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  8. 2019Adversarial Training and Robustness for Multiple Perturbationscited by 182
  9. 2019Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AIcited by 63
  10. 2018Stakeholders in Explainable AIcited by 48
  11. 2020A systematic review and taxonomy of explanations in decision support and recommender systemscited by 45
  12. 2019When Explainability Meets Adversarial Learning: Detecting Adversarial Examples using SHAP Signaturescited by 40
5 more
  1. 2021Principles of Explanation in Human-AI Systemscited by 25
  2. 2019Generating Counterfactual and Contrastive Explanations using SHAPcited by 23
  3. 2017Interpreting Classifiers through Attribute Interactions in Datasetscited by 8
  4. 2021A Work-Centered Approach for Cyber-Physical-Social System Design: Applications in Aerospace Industrial Inspectioncited by 1
  5. 2021Extending System Performance Past the Boundaries of Technical Maturity: Human-Agent Teamwork Perspective for Industrial Inspectioncited by 1

Built on by

Not cited yet.