arXiv:2610.10301v1 Announce Type: new Abstract: Modern applications of AI rely on increasingly complex models. Explainable AI (XAI) has emerged as a set of techniques aimed at improving model transpa...
arXiv:2607. 24730v1 Announce Type: cross Abstract: Computer vision models have become highly effective for medical applications, yet their black-box nature continues to undermine clinician trust.
The paper presents a plug‑and‑play framework that uses concept-based interpretation to debug medical imaging models. By aligning a single‑modality encoder with BioMedCLIP, the authors build a Concept Bottleneck Model that allows concept‑level interventions to distinguish causal from spurious features. Experiments on Mayo Clinic ultrasound and CheXpert chest X‑ray data show that these interventions can reliably diagnose model issues and even improve performance through guided fine‑tuning.
arXiv:2607. 14315v1 Announce Type: cross Abstract: In this paper, we present a comprehensive framework for assessing the explainability of various XAI methods, such as LIME and SHAP, across multiple datasets and machine learning models, with the ultimate goal of creating a unified multidimensional explainability score.
The paper introduces SMILE, a self‑explainable multimodal information bottleneck framework for medical diagnosis. It jointly optimizes predictive accuracy and modality‑specific explainability by selecting the most informative elements within each data modality. Experiments on diverse medical datasets show strong diagnostic performance, including a 9.1‑percentage‑point accuracy gain on the iCTCF dataset, and provide transparent, modality‑aware explanations that enhance both explainability and generalization.
The paper introduces a synthetic ground‑truth framework for evaluating explainable AI (XAI) methods, addressing the lack of reliable evaluation procedures. By using controlled interventions to create datasets where the importance of input components is known, the framework generates ground‑truth explanations that align with the model’s actual decision process. The authors apply this approach to binary images, tabular data, and time series, and find that nine popular XAI methods exhibit significant limitations, underscoring the need for intervention‑based benchmarks.
The paper introduces ExCIR, a new explainability metric that addresses limitations of existing post‑hoc explainers by accurately handling correlated features and avoiding costly perturbations. ExCIR is theoretically grounded, computationally efficient, and remains stable under noise and sampling variations. Experiments on EEG, synthetic vehicular data, Digits, and Cats‑Dogs datasets show that ExCIR provides more interpretable feature explanations than current methods, and its information‑theoretic extension supports multi‑output and class‑conditioned explanations at scale.
arXiv:2608. 10766v1 Announce Type: new Abstract: Explainable Artificial Intelligence (XAI) seeks to explain how an Artificial Intelligence (AI) system arrived at a particular decision.
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:2607. 07316v1 Announce Type: new Abstract: This article offers a comprehensive overview of mechanistic interpretability, an emerging field that seeks to reverse-engineer the internal algorithms of modern neural networks.
The paper argues that explainable AI for computer vision has focused too much on developing interpretability methods rather than assessing how interpretable the models themselves are. It proposes a shift toward model-centric evaluation, using existing tools to compare what different models represent and compute, and emphasizes the need to measure whether humans can truly understand these models. The authors review the current toolbox, survey limited model comparison work, draw parallels to systems neuroscience, and outline a future agenda for model-focused XAI.
arXiv:2603. 02221v2 Announce Type: replace-cross Abstract: In clinical tabular prediction, classical machine learning models with feature engineering often outperform neural methods.