A Two-Dimensional Explanation Framework to Classify AI as Incomprehensible, Interpretable, or Understandable

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Abstract

Because of recent and rapid developments in Artificial Intelligence (AI), humans and AI-systems increasingly work together in human-agent teams. However, in order to effectively leverage the capabilities of both, AI-systems need to be understandable to their human teammates. The branch of eXplainable AI (XAI) aspires to make AI-systems more understandable to humans, potentially improving human-agent teamwork. Unfortunately, XAI literature suffers from a lack of agreement regarding the definitions of and relations between the four key XAI-concepts: transparency, interpretability, explainability, and understandability. Inspired by both XAI and social sciences literature, we present a two-dimensional framework that defines and relates these concepts in a concise and coherent way, yielding a classification of three types of AI-systems: incomprehensible, interpretable, and understandable. We also discuss how the established relationships can be used to guide future research into XAI, and how the framework could be used during the development of AI-systems as part of human-AI teams.
Original languageEnglish
Title of host publicationExplainable and Transparent AI and Multi-Agent Systems
Subtitle of host publicationThird International Workshop, EXTRAAMAS 2021
EditorsDavide Calvaresi, Amro Najjar, Michael Winikoff, Kary Främling
Place of PublicationCham
PublisherSpringer
Pages119-138
Number of pages20
ISBN (Electronic)978-3-030-82017-6
ISBN (Print)978-3-030-82016-9
DOIs
Publication statusPublished - 2021
EventEXTRAAMAS 2021: Third International Workshop on Explainable, Transparent Autonomous Agents and Multi-Agent Systems - Virtual at London, United Kingdom
Duration: 3 May 20217 May 2021

Publication series

NamePart of the Lecture Notes in Computer Science book series
PublisherSpringer
Volume12688

Workshop

WorkshopEXTRAAMAS 2021
CountryUnited Kingdom
CityVirtual at London
Period3/05/217/05/21

Bibliographical note

Accepted author manuscript

Keywords

  • Explainability
  • Explainable AI
  • Human-agent teaming
  • Interpretability
  • Transparency
  • Understandability

Fingerprint

Dive into the research topics of 'A Two-Dimensional Explanation Framework to Classify AI as Incomprehensible, Interpretable, or Understandable'. Together they form a unique fingerprint.

Cite this