# The Susceptibility of Example-Based Explainability Methods to Class Outliers Source: [The Susceptibility of Example-Based Explainability Methods to Class Outliers]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:37:02.192Z Authors: Ikhtiyor Nematov, Dimitris Sacharidis, Tomer Sagi, Katja Hose Published: 2024-07-30T09:20:15.000Z ## Abstract This study explores the impact of class outliers on the effectiveness of example-based explainability methods for black-box machine learning models. We reformulate existing explainability evaluation metrics, such as correctness and relevance, specifically for example-based methods, and introduce a new metric, distinguishability. Using these metrics, we highlight the shortcomings of current example-based explainability methods, including those who attempt to suppress class outliers. We conduct experiments on two datasets, a text classification dataset and an image classification dataset, and evaluate the performance of four state-of-the-art explainability methods. Our findings underscore the need for robust techniques to tackle the challenges posed by class outliers. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()