mlsanityData to 14 Oct 2026

"Explanation" is Not a Technical Term: The Problem of Ambiguity in XAI

arXiv 2207.00007 ↗First posted 27 Jun 2022cs.HC cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

There is broad agreement that Artificial Intelligence (AI) systems, particularly those using Machine Learning (ML), should be able to "explain" their behavior. Unfortunately, there is little agreement as to what constitutes an "explanation." This has caused a disconnect between the explanations that systems produce in service of explainable Artificial Intelligence (XAI) and those explanations that users and other audiences actually need, which should be defined by the full spectrum of functional roles, audiences, and capabilities for explanation. In this paper, we explore the features of explanations and how to use those features in evaluating their utility. We focus on the requirements for explanations defined by their functional role, the knowledge states of users who are trying to understand them, and the availability of the information needed to generate them. Further, we discuss the risk of XAI enabling trust in systems without establishing their trustworthiness and define a critical next step for the field of XAI to establish metrics to guide and ground the utility of system-generated explanations.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 11 of its 24 references that are in the map. First posted on arXiv 27 Jun 2022.

Builds on

11 of 24 references.

References · 11

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,206
  4. 2018Sanity Checks for Saliency Mapscited by 1,156
  5. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  6. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  7. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 443
  8. 2022The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspectivecited by 159
  9. 2018Stop Explaining Black Box Machine Learning Models for High Stakes Decisions and Use Interpretable Models Insteadcited by 40
  10. 2020Machine Learning Explainability for External Stakeholderscited by 17
  11. 2020Foundations of Explainable Knowledge-Enabled Systemscited by 6

Built on by

Cited by year

Citing papers per year: 2023: 4.

4 papers.

  1. 2023Manipulation Risks in Explainable AI: The Implications of the Disagreement Problemcited by 7
  2. 2023Understanding User Preferences in Explainable Artificial Intelligence: A Survey and a Mapping Function Proposalcited by 1
  3. 2023Fiduciary Responsibility: Facilitating Public Trust in Automated Decision Makingcited by 0
  4. 2023What's meant by explainable model: A Scoping Reviewcited by 0