A consensus-driven probabilistic approach generates robust counterfactual explanations by modeling data under varying classifier agreement levels using conditional normalizing flows.
Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Evidence-grounded LLM triage with structured contracts and counterfactual validation achieves PR-AUC 0.75 and high faithfulness scores on synthetic AML benchmarks.
citing papers explorer
-
A Probabilistic Consensus-Driven Approach for Robust Counterfactual Explanations
A consensus-driven probabilistic approach generates robust counterfactual explanations by modeling data under varying classifier agreement levels using conditional normalizing flows.
-
Explainable AML Triage with LLMs: Evidence Retrieval and Counterfactual Checks
Evidence-grounded LLM triage with structured contracts and counterfactual validation achieves PR-AUC 0.75 and high faithfulness scores on synthetic AML benchmarks.