Repository logo
Log In(current)
  1. Home
  2. Prodotti della ricerca
  3. D. Contributo in Atti di convegno
  4. D1. Contributo in Atti di convegno
  5. Irrelevant Explanations: a logical formalization and a case study

Irrelevant Explanations: a logical formalization and a case study

Author(s)
Colucci, Simona and and and and
Di Noia, Tommaso
Donini, Francesco Maria  
Pomo, Claudio
Di Sciascio, Eugenio
Date Issued
2023
Type
conferenceObject
Volume
3518
Start Page
67
End Page
75
Journal
CEUR WORKSHOP PROCEEDINGS  
Abstract
Explaining the behavior of AI-based tools, whose results may be unexpected even to experts, has become a major request from society and a major concern of AI practitioners and theoreticians. In this position paper we raise two points: (1) irrelevance is more amenable to a logical formalization than relevance; (2) since effective explanations must take into account both the context and the receiver of the explanations (called the explainee) so it should be also for the definition of irrelevance. We propose a general, logical framework characterizing context-aware and receiver-aware irrelevance, and provide a case study on an existing tool, based on Semantic Web, that prunes irrelevant parts of an explanation. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Handle
http://hdl.handle.net/2067/50500
Related items
Metrics
Conference(s)
4th Italian Workshop on Explainable Artificial Intelligence (XAI.it 2023)

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science

  • Accessibility settings
  • Privacy policy
  • End User Agreement
  • Send Feedback
Repository logo COAR Notify