Two challenges for CI trustworthiness and how to address them
(2017)
Abstract
We argue that, to be trustworthy, Computa-
tional Intelligence (CI) has to do what it is
entrusted to do for permissible reasons and
to be able to give rationalizing explanations
of its behavior which are accurate and gras-
pable. We support this claim by drawing par-
allels with trustworthy human persons, and we
show what difference this makes in a hypo-
thetical CI hiring system. Finally, we point out
two challenges for trustworthy CI and sketch
a mechanism which could be used to gener-
ate sufficiently accurate as well as graspable
rationalizing explanations for CI behavior.
Keywords
Categories
(categorize this paper)
Reprint years
2017
PhilPapers/Archive ID
SCHTCF-9
Upload history
Archival date: 2017-12-30
View other versions
View other versions
Added to PP index
2017-10-09
Total views
104 ( #51,607 of 71,429 )
Recent downloads (6 months)
8 ( #61,073 of 71,429 )
2017-10-09
Total views
104 ( #51,607 of 71,429 )
Recent downloads (6 months)
8 ( #61,073 of 71,429 )
How can I increase my downloads?
Downloads since first upload
This graph includes both downloads from PhilArchive and clicks on external links on PhilPapers.