cs.AIApr 17, 2026

Towards Rigorous Explainability by Feature Attribution

Authors: Olivier Létoffé, Xuanxiang Huang, Joao Marques-Silva

Organizations: IRIT, University of Toulouse France · Nanyang Technological University, Singapore · ICREA & Univ. Lleida, Spain

Abstract

For around a decade, non-symbolic methods have been the option of choice when explaining complex machine learning (ML) models. Unfortunately, such methods lack rigor and can mislead human decision-makers. In high-stakes uses of ML, the lack of rigor is especially problematic. One prime example of provable lack of rigor is the adoption of Shapley values in explainable artificial intelligence (XAI), with the tool SHAP being a ubiquitous example. This paper overviews the ongoing efforts towards using rigorous symbolic methods of XAI as an alternative to non-rigorous non-symbolic approaches, concretely for assigning relative feature importance.

Explore similar work

CardsList
  1. Beyond Shapley: Efficient Computation of Asymmetric Shapley Values

    Jun 23, 2026Ezequiel Companeetz, Santiago Cifuentes, Sergio AbriolaShapley ValueInterpretable Models

  2. RelShap: Relationally Consistent Shapley Explanations

    Aug 11, 2026Seungeun Lee, Joao Fonseca, Julia StoyanovichShapley Value