A novel perspective is introduced by embedding FIMs within a hypothesis-testing framework based on Weight of Evidence (WoE), which quantifies how strongly the observed evidence supports any given hypothesis on feature importance.
Abstract
Feature importance Methods (FIMs) are widely used in Explainable AI to interpret model predictions, yet attribution scores alone often provide limited insight into the underlying reasoning process. In this work, we introduce a novel perspective by embedding FIMs within a hypothesis-testing framework based on Weight of Evidence (WoE). We quantify how strongly the observed evidence supports any given hypothesis on feature importance. The reference hypothesis can stem from domain knowledge, ground truth, or be derived from the FIM itself. This formulation enables a principled evaluation of FIMs, capturing both their alignment with prior knowledge and their variability. We further provide theoretical results linking WoE to attribution variance. Empirical results shows the applicability and flexibility of our strategy analyzing LIME and SHAP explanations in settings with different reference hypotheses. Overall, our framework offers a complementary tool for assessing FIMs through a contrastive, evidence-based lens.
One of the main limitations for the trust in the use of machine learning models is the understanding of how they produce their predictions. This limitation is related to an increasing demand for transparency in decision-making. Interpretability refers to how well a user can understand the model’s decision-making proces...
G. Y. Shimizu, Rafael Izbicki, Fernando Rezende Zagatti et al.· Journal of the Brazilian Com...· 3 citations
Contextual scores represent assessment items through their similarities to reference words in an external corpus. We examine the semantic structure of scores for 40 TIMSS mathematics scored units using a partially specified two-step factor procedure. A search across factor counts identifies a persistent seven-group str...
Chain-of-thought (CoT) can sound plausible yet be unfaithful to the model's underlying reasoning. Most prior work probes CoT faithfulness through input--output behavior or input attributions, leaving internal computation largely underexplored. We instead cast faithfulness as internal concept grounding: Does a large lan...
Qianli Wang, Yilong Wang, Dennis Wei et al.· 0 citations
This work evaluates ten instruction-tuned models from the LLaMA-3 and Qwen-2.5 families, measuring faithfulness, minimality, and alignment with human-annotated rationales and shows that model scale is the strongest determinant of explanation quality.
Giannis Kalyvas, Giorgos Filandrianos, Orfeas Menis-Mastromichalakis et al.· 0 citations
Explainability in recommender systems (RS) remains a pivotal challenge. Counterfactual explanations have emerged as a particularly actionable paradigm, offering intuitive “what-if” reasoning. However, their evaluation lacks principled standards. Current metrics primarily assess whether explanations change the top-ranke...
Amir Reza Mohammadi, Andreas Peintner, Michael M. Müller et al.· ACM Transactions on Recommen...· 0 citations
Current evaluation of metaphor explanations relies mainly on holistic quality ratings, revealing little about how explanation quality is structured or where human judgments agree and diverge. We introduce a cognitively motivated framework that decomposes metaphor explanation quality into six theoretically grounded dime...
Ana Naveriani, Jakob Suchan, S. Zoia et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.
