CBR driven interactive explainable AI

Thumbnail Image
Files
paper_70.pdf(9.84 MB)
Accepted Version
Date
2023-07-30
Authors
Wijekoon, Anjana
Wiratunga, Nirmalie
Martin, Kyle
Corsar, David
Nkisi-Orji, Ikechukwu
Palihawadana, Chamath
Bridge, Derek G.
Pradeep, Preeja
Diaz Agudo, Belen
Caro-Martínez, Marta
Journal Title
Journal ISSN
Volume Title
Publisher
Springer Nature Switzerland AG
Published Version
https://doi.org/10.1007/978-3-031-40177-0_11
Research Projects
Organizational Units
Journal Issue
Abstract
Explainable AI (XAI) can greatly enhance user trust and satisfaction in AI-assisted decision-making processes. Numerous explanation techniques (explainers) exist in the literature, and recent findings suggest that addressing multiple user needs requires employing a combination of these explainers. We refer to such combinations as explanation strategies. This paper introduces iSee - Intelligent Sharing of Explanation Experience, an interactive platform that facilitates the reuse of explanation strategies and promotes best practices in XAI by employing the Case-based Reasoning (CBR) paradigm. iSee uses an ontology-guided approach to effectively capture explanation requirements, while a behaviour tree-driven conversational chatbot captures user experiences of interacting with the explanations and provides feedback. In a case study, we illustrate the iSee CBR system capabilities by formalising a real-world radiograph fracture detection system and demonstrating how each interactive tools facilitate the CBR processes.
Description
Keywords
Interactive XAI , Ontology-based CBR , Conversational AI
Citation
Wijekoon, A., Wiratunga, N., Martin, K., Corsar, D., Nkisi-Orji, I., Palihawadana, C., Bridge, D., Pradeep, P., Diaz Agudo, B. and Caro-Martínez, M. (2023) 'CBR driven interactive explainable AI', in Massie, S. and Chakraborti, S. (eds) Case-Based Reasoning Research and Development. ICCBR 2023, Lecture Notes in Computer Science, 14141, pp. 169-184. Springer, Cham. https://doi.org/10.1007/978-3-031-40177-0_11
Link to publisher’s version
URI
https://hdl.handle.net/10468/15099
Collections
Insight Centre for Data Analytics - Conference Items
Computer Science - Conference Items
Copyright
© 2023, the Authors, under exclusive license to Springer Nature Switzerland AG. This is a post-peer-review, pre-copyedit version of a paper published as: Wijekoon, A. et al. (2023). CBR Driven Interactive Explainable AI. In: Massie, S., Chakraborti, S. (eds) Case-Based Reasoning Research and Development. ICCBR 2023. Lecture Notes in Computer Science, vol 14141. Springer, Cham Springer, Cham. The final authenticated version is available online at: https://doi.org/10.1007/978-3-031-40177-0_11