<ul><li>ExplainBench is an open-source benchmarking suite designed for evaluating local model explanations in critical domains like criminal justice, finance, and healthcare.</li><li>It aims to standardize and facilitate the comparative assessment of explanation techniques like SHAP, LIME, and counterfactual methods, especially in fairness-sensitive contexts.</li><li>ExplainBench offers unified wrappers for explanation algorithms, integrates pipelines for model training and explanation generation, and supports evaluation using metrics like fidelity, sparsity, and robustness.</li><li>This framework includes a graphical interface for interactive exploration, is packaged as a Python module, and is demonstrated on datasets like COMPAS, UCI Adult Income, and LendingClub to showcase its utility in promoting interpretable machine learning and accountability in AI systems.</li></ul>

ExplainBench: A Benchmark Framework for Local Model Explanations in Fairness-Critical Applications

Discover more