KR2024Proceedings of the 21st International Conference on Principles of Knowledge Representation and ReasoningProceedings of the 21st International Conference on Principles of Knowledge Representation and Reasoning

Hanoi, Vietnam. November 2-8, 2024.

Edited by

ISSN: 2334-1033
ISBN: 978-1-956792-05-8

Sponsored by
Published by

Copyright © 2024 International Joint Conferences on Artificial Intelligence Organization

Contestable AI Needs Computational Argumentation

  1. Francesco Leofante(Imperial College London)
  2. Hamed Ayoobi(Imperial College London)
  3. Adam Dejl(Imperial College London)
  4. Gabriel Freedman(Imperial College London)
  5. Deniz Gorur(Imperial College London)
  6. Junqi Jiang(Imperial College London)
  7. Guilherme Paulino-Passos(Imperial College London)
  8. Antonio Rago(Imperial College London)
  9. Anna Rapberger(Imperial College London)
  10. Fabrizio Russo(Imperial College London)
  11. Xiang Yin(Imperial College London)
  12. Dekai Zhang(Imperial College London)
  13. Francesca Toni(Imperial College London)

Keywords

  1. Autonomous Decision Making-General

Abstract

AI has become pervasive in recent years, but state-of-the-art approaches predominantly neglect the need for AI systems to be contestable. Instead, contestability is advocated by AI guidelines (e.g. by the OECD) and regulation of automated decision-making (e.g. GDPR). In this position paper we explore how contestability can be achieved computationally in and for AI. We argue that contestable AI requires dynamic (human-machine and/or machine-machine) explainability and decision-making processes, whereby machines can

1. interact with humans and/or other machines to progressively explain their outputs and/or their reasoning as well as assess grounds for contestation provided by these humans and/or other machines, and 2. revise their decision-making processes to redress any issues successfully raised during contestation. Given that much of the current AI landscape is tailored to static AIs, the need to accommodate contestability will require a radical rethinking, that, we argue, computational argumentation is ideally suited to support.