What Does Explainable AI Really Mean? A New Conceptualization of Perspectives

2017/10/02 by Derek Doran, Doran, Derek, Sarah Schulz +3 · 10 citations
Computer Science · #Artificial Intelligence (cs.AI) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1710.00794

openalex publication_date 2017/10/02 · openalex created_date 2017/10/20 · openalex updated_date 2026/07/28

Abstract

We characterize three notions of explainable AI that cut across research fields: opaque systems that offer no insight into its algo- rithmic mechanisms; interpretable systems where users can mathemat- ically analyze its algorithmic mechanisms; and comprehensible systems that emit symbols enabling user-driven explanations of how a conclusion is reached. The paper is motivated by a corpus analysis of NIPS, ACL, COGSCI, and ICCV/ECCV paper titles showing differences in how work on explainable AI is positioned in various fields. We close by introducing a fourth notion: truly explainable systems, where automated reasoning is central to output crafted explanations without requiring human post processing as final step of the generative process.

Citations

• Image Captioning with Semantic Attention
• The Mythos of Model Interpretability

Cited by

• Optimality Principles and Neural Ordinary Differential Equations-based Process Modeling for Distributed Control
• Scientific Calculator for Designing Trojan Detectors in Neural Networks
• XAlgo: a Design Probe of Explaining Algorithms' Internal States via Question-Answering
• Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI
• Teaching Solid Mechanics to Artificial Intelligence: a fast solver for\n heterogeneous solids
• A Manifesto for Future Generation Cloud Computing: Research Directions for the Next Decade
• Generalized Constraints as A New Mathematical Problem in Artificial Intelligence: A Review and Perspective
• Ten AI Stepping Stones for Cybersecurity
• Explainable Machine Learning with Prior Knowledge: An Overview
• Rhetorical XAI: Explaining AI's Benefits as well as its Use via Rhetorical Design

Related

• Explainability Is in the Mind of the Beholder: Establishing the Foundations of Explainable Artificial Intelligence
• Foundations of Explainable Knowledge-Enabled Systems
• One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
• Towards Quantification of Explainability in Explainable Artificial Intelligence Methods
• Helpful, Misleading or Confusing: How Humans Perceive Fundamental Building Blocks of Artificial Intelligence Explanations