PACE is a modular neuro-symbolic system that uses Answer Set Programming to enforce domain constraints when generating actionable counterfactuals for an MLP classifier on the Adult Income dataset.
Explaining machine learning classifiers through diverse counterfactual explanations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PACE: A Neuro-Symbolic Framework for Plausible and Actionable Counterfactual Explanations
PACE is a modular neuro-symbolic system that uses Answer Set Programming to enforce domain constraints when generating actionable counterfactuals for an MLP classifier on the Adult Income dataset.