Saved in:
Bibliographic Details
Main Authors: Létoffé, Olivier, Huang, Xuanxiang, Marques-Silva, Joao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.15898
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917539765813248
author Létoffé, Olivier
Huang, Xuanxiang
Marques-Silva, Joao
author_facet Létoffé, Olivier
Huang, Xuanxiang
Marques-Silva, Joao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_15898
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Rigorous Explainability by Feature Attribution
Létoffé, Olivier
Huang, Xuanxiang
Marques-Silva, Joao
Artificial Intelligence
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.
title Towards Rigorous Explainability by Feature Attribution
topic Artificial Intelligence
url https://arxiv.org/abs/2604.15898