Citation

BibTex format

@inproceedings{Albini:2022:10.1007/978-3-031-18843-5_19,
author = {Albini, E and Rago, A and Baroni, P and Toni, F},
doi = {10.1007/978-3-031-18843-5_19},
pages = {279--294},
publisher = {Springer},
title = {Descriptive accuracy in explanations: the case of probabilistic classifiers},
url = {http://dx.doi.org/10.1007/978-3-031-18843-5_19},
year = {2022}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - A user receiving an explanation for outcomes produced by an artificially intelligent system expects that it satisfies the key property of descriptive accuracy (DA), i.e. that the explanation contents are in correspondence with the internal working of the system. Crucial as this property appears to be, it has been somehow overlooked in the XAI literature to date. To address this problem, we consider the questions of formalising DA and of analysing its satisfaction by explanation methods. We provide formal definitions of naive, structural and dialectical DA, using the family of probabilistic classifiers as the context for our analysis. We evaluate the satisfaction of our given notions of DA by several explanation methods, amounting to two popular feature-attribution methods from the literature and a novel form of explanation that we propose and complement our analysis with experiments carried out on a varied selection of concrete probabilistic classifiers.
AU - Albini,E
AU - Rago,A
AU - Baroni,P
AU - Toni,F
DO - 10.1007/978-3-031-18843-5_19
EP - 294
PB - Springer
PY - 2022///
SP - 279
TI - Descriptive accuracy in explanations: the case of probabilistic classifiers
UR - http://dx.doi.org/10.1007/978-3-031-18843-5_19
UR - http://hdl.handle.net/10044/1/98451
ER -

Contact us

Artificial Intelligence Network
South Kensington Campus
Imperial College London
SW7 2AZ

To reach the elected speaker of the network, Dr Rossella Arcucci, please contact:

ai-speaker@imperial.ac.uk

To reach the network manager, Diana O'Malley - including to join the network - please contact:

ai-net-manager@imperial.ac.uk