Search Results for author:
Found 5 papers, 0 papers with code
On the Importance of Application-Grounded Experimental Design for Evaluating Explainable ML Methods
Most existing evaluations of explainable machine learning (ML) methods rely on simplifying assumptions or proxies that do not reflect real-world use cases; the handful of more robust evaluations on real-world settings have shortcomings in their design, resulting in limited conclusions of methods' real-world utility.
ConceptDistil: Model-Agnostic Distillation of Concept Explanations
Concept-based explanations aims to fill the model interpretability gap for non-technical humans-in-the-loop.
Weakly Supervised Multi-task Learning for Concept-based Explainability
In ML-aided decision-making tasks, such as fraud detection or medical diagnosis, the human-in-the-loop, usually a domain-expert without technical ML knowledge, prefers high-level concept-based explanations instead of low-level explanations based on model features.
How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations
We conducted an experiment following XAI Test to evaluate three popular post-hoc explanation methods -- LIME, SHAP, and TreeInterpreter -- on a real-world fraud detection task, with real data, a deployed ML model, and fraud analysts.
Decision Making
Explainable Artificial Intelligence (XAI)
+1
Teaching the Machine to Explain Itself using Domain Knowledge
Moreover, we collect the domain feedback from a pool of certified experts and use it to ameliorate the model (human teaching), hence promoting seamless and better suited explanations.
