iSee: advancing multi-shot explainable AI using case-based recommendations.

Wijekoon, Anjana; Wiratunga, Nirmalie; Corsar, David; Martin, Kyle; Nkisi-Orji, Ikechukwu; Palihawadana, Chamath; Caro-Martínez, Marta; Díaz-Agudo, Belen; Bridge, Derek; Liret, Anne

Abstract

Explainable AI (XAI) can greatly enhance user trust and satisfaction in AI-assisted decision-making processes. Recent findings suggest that a single explainer may not meet the diverse needs of multiple users in an AI system; indeed, even individual users may require multiple explanations. This highlights the necessity for a “multi-shot” approach, employing a combination of explainers to form what we introduce as an “explanation strategy”. Tailored to a specific user or a user group, an “explanation experience” describes interactions with personalised strategies designed to enhance their AI decision-making processes. The iSee platform is designed for the intelligent sharing and reuse of explanation experiences, using Case-based Reasoning to advance best practices in XAI. The platform provides tools that enable AI system designers, i.e. design users, to design and iteratively revise the most suitable explanation strategy for their AI system to satisfy end-user needs. All knowledge generated within the iSee platform is formalised by the iSee ontology for interoperability. We use a summative mixed methods study protocol to evaluate the usability and utility of the iSee platform with six design users across varying levels of AI and XAI expertise. Our findings confirm that the iSee platform effectively generalises across applications and its potential to promote the adoption of XAI best practices.

Citation

WIJEKOON, A., WIRATUNGA, N., CORSAR, D., MARTIN, K., NKISI-ORJI, I., PALIHAWADANA, C., CARO-MARTÍNEZ, M., DÍAZ-AGUDO, B., BRIDGE, D. and LIRET, A. 2024. iSee: advancing multi-shot explainable AI using case-based recommendations. In Endriss, U., Melo, F.S., Bach, K., et al. (eds.) ECAI 2024: proceedings of the 27th European conference on artificial intelligence, co-located with the 13th conference on Prestigious applications of intelligent systems (PAIS 2024), 19–24 October 2024, Santiago de Compostela, Spain. Frontiers in artificial intelligence and applications, 392. Amsterdam: IOS Press [online], pages 4626-4633. Available from: https://doi.org/10.3233/FAIA241057

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 27th European conference on artificial intelligence (ECAI 2024): celebrating the past inspiring the future, co-located with 13th Conference on prestigious applications of intelligent systems (PAIS 2024)
• Start Date: Oct 19, 2024
• End Date: Oct 24, 2024
• Acceptance Date: Jul 4, 2024
• Online Publication Date: Oct 16, 2024
• Publication Date: Dec 31, 2024
• Deposit Date: Feb 13, 2025
• Publicly Available Date: Feb 13, 2025
• Print ISSN: 0922-6389
• Electronic ISSN: 1879-8314
• Publisher: IOS Press
• Peer Reviewed: Peer Reviewed
• Volume: 392
• Pages: 4626-4633
• Series Title: Frontiers in Artificial Intelligence and Applications
• Series Number: 392
• DOI: https://doi.org/10.3233/FAIA241057
• Keywords: Explainable artificial intelligence (XAI); AI-assisted decision-making processes; AI system designers
• Public URL: https://rgu-repository.worktribe.com/output/2702382