Towards Rigorous Explainability by Feature Attribution

Computer Science > Artificial Intelligence [Submitted on 17 Apr 2026] Towards Rigorous Explainability by Feature Attribution Olivier Létoffé, Xuanxiang Huang, Joao Marques-Silva 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. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.15898 [cs.AI]   (or arXiv:2604.15898v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.15898 Focus to learn more Submission history From: Xuanxiang Huang [view email] [v1] Fri, 17 Apr 2026 09:56:17 UTC (62 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)