Everyday Argumentative Explanations for Classification
Files
Publication date
2022
Authors
van Lente, Jowan
Borg, AnneMarie
Bex, Floris
Editors
Kuhlmann, Isabelle
Mumford, Jack
Sarkadi, Stefan
Advisors
Supervisors
DOI
Document Type
Part of book
Metadata
Show full item recordCollections
License
cc_by
Abstract
In this paper we study everyday explanations for classification tasks with formal argumentation. Everyday explanations describe how humans explain in day-to-day life, which is important when explaining decisions of AI systems to lay users. We introduce EVAX, a model-agnostic explanation method for classifiers with which contrastive, selected and social explanations can be generated. The resulting explanations can be adjusted in their size and retain high fidelity scores (an average of 0.95)
Keywords
Explainable artificial intelligence, Formal Argumentation, Classification
Citation
van Lente, J, Borg, A & Bex, F 2022, Everyday Argumentative Explanations for Classification. in I Kuhlmann, J Mumford & S Sarkadi (eds), Argumentation & Machine Learning : Proceedings of the 1st Workshop on Argumentation & Machine Learning co-located with 9th International Conference on Computational Models of Argument (COMMA 2022). vol. 3208, CEUR Workshop Proceedings, vol. 3208, CEUR WS, pp. 14-26. < http://ceur-ws.org/Vol-3208/paper2.pdf >