The paper formalizes contrastive explanations in description logics that answer why an ABox assertion P holds instead of a foil Q, with definitions, properties in EL and ALC, and an implementation.
In: AIES ’20: AAAI/ACM Conference on AI, Ethics, and Society
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2verdicts
UNVERDICTED 2representative citing papers
A scoping review of AIES and FAccT literature concludes that AI trustworthiness research prioritizes technical precision over social, ethical, and institutional factors, leaving the sociotechnical nature of AI systems underexplored.
citing papers explorer
-
Rethinking Explanations: Formalizing Contrast in Description Logics
The paper formalizes contrastive explanations in description logics that answer why an ABox assertion P holds instead of a foil Q, with definitions, properties in EL and ALC, and an implementation.
-
Understanding AI Trustworthiness: A Scoping Review of AIES & FAccT Articles
A scoping review of AIES and FAccT literature concludes that AI trustworthiness research prioritizes technical precision over social, ethical, and institutional factors, leaving the sociotechnical nature of AI systems underexplored.