The paper highlights that many current model interpretation techniques overlook the baseline, leading to inaccurate or incorrect explanations. It redefines the interpretation task, unifies gradient-based, Integrated Gradients, and Taylor expansion methods, and explicitly identifies appropriate baselines for each. The authors critique existing methods, propose a new interpretation approach with a clear baseline, and demonstrate its improved performance across layers.
arXiv:2606. 10877v1 Announce Type: new Abstract: Occlusion-based attribution methods provide an intuitive way to estimate feature importance by perturbing input features and measuring the resulting change in model output.
The paper proposes a new evaluation test for explanation methods: if an explanation accurately captures how a model uses its features, one should be able to reconstruct the model’s predictions from it. The authors convert explanations into predictors by summing feature effects and assess how well these predictors reproduce the model on unseen data, without any fitting. They apply this test to partial dependence plots, accumulated local effects, SHAP, and LIME across multiple datasets and model families, showing that the best method depends on feature dependence and that some existing quality metrics can favor flawed explanations.
arXiv:2606. 03885v1 Announce Type: new Abstract: Feature attribution methods explain predictions by assigning importance scores to input features.
The paper introduces a straightforward evaluation method for explanation techniques: by converting each explanation into a predictor that sums the feature effects, the authors assess how accurately this predictor reproduces the original model’s predictions on unseen data. This approach applies to any explanation expressible as a function of features and is demonstrated on PDP, ALE, SHAP, and LIME. The authors theoretically show that summing partial dependence curves yields the optimal additive summary when features are independent, but this property fails with dependent features, and empirical results across diverse datasets confirm that the best-performing method depends on feature dependence.
The paper introduces Adaptive Derivative-Ordered Random Explanation (ADORE), a unified framework that uses first- and second-order derivatives to capture nonlinear feature interactions and feature-sample dynamics. ADORE combines global feature importance with local sample contributions, quantifying both magnitude and direction of feature impact while identifying critical samples. It achieves computational efficiency via randomized SVD and dynamic sparsity detection, outperforming LIME and SHAP across tabular, text, and image data, and is released as an open-source Python package on GitHub.
arXiv:2609.07876v1 Announce Type: cross Abstract: Recent methods in language model interpretability employ techniques such as sparse autoencoders to decompose residual stream contributions into linea...
arXiv:2505. 03201v4 Announce Type: replace-cross Abstract: Integrated Gradients (IG) is a widely used attribution method in explainable AI, particularly in computer vision applications where reliable feature attribution is essential.
arXiv:2601. 21944v3 Announce Type: replace Abstract: The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability.
arXiv:2608. 12299v1 Announce Type: cross Abstract: Class activation mapping (CAM) is one of the most widely used visual explanation families in explainable artificial intelligence.
arXiv:2607. 24645v1 Announce Type: cross Abstract: The wide-scale use of sparse autoencoders (SAEs) as interpretability tools is limited by inconsistent links between SAE features and model behavior.
arXiv:2607. 29614v1 Announce Type: cross Abstract: The rapid adoption of deep learning models in high-risk domains has intensified the need for trustworthy Explainable Artificial Intelligence (XAI).
arXiv:2607. 10803v1 Announce Type: cross Abstract: Understanding which parameters are influential in Large Language Models (LLMs) is central to improving their efficiency, reliability, and interpretability.