arXiv AI By Eddie Conti, Claudio Daka, \'Alvaro Parafita, Antonio L. Alfeo, Axel Brando, Mario G. C. A. Cimino

Assessing Alignment and Stability of Feature Importance Explanations via Weight of Evidence

Read the original on arXiv AI →

The paper introduces a hypothesis‑testing framework that embeds feature importance methods (FIMs) within a Weight of Evidence (WoE) analysis. By quantifying how strongly observed evidence supports a given hypothesis—whether from domain knowledge, ground truth, or the FIM itself—the approach evaluates FIM alignment and variability. The authors provide theoretical links between WoE and attribution variance and demonstrate the method on LIME and SHAP explanations across varied reference hypotheses.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning
5d ago

Evaluating Explanation Methods by the Predictors They Induce

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.

By Jacob Selb{\ae}k, Hugo L. Hammer
arXiv Machine Learning
Sep 7

ProToMEx: Rapid, Interpretable Explanations via Structured Representations

ProToMEx is a new explainability framework that uses Probabilistic Topic Models to learn latent topics representing high‑level reasons behind a classifier’s decisions, moving beyond simple feature attribution. It provides both global and local explanations, revealing multiple co‑existing reasons for individual predictions. Empirical results show that ProToMEx achieves comparable fidelity to SHAP and LIME while being 30–40× faster on standard tabular and synthetic datasets.

By Athina Georgara, Adarsh Valoor, Sarvapali D. Ramchurn
arXiv AI
Jul 17

Towards a Unified Multidimensional Explainability Metric: Evaluating Trustworthiness in AI Models

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.

By Georgios Makridis, Georgios Fatouros, Athanasios Kiourtis, Dimitrios Kotios, Vasileios Koukos, Dimosthenis Kyriazis, Jonh Soldatos