Aligned explanations in neural networks

Corentin Lobet and Francesca Chiaromonte

LEM Papers Series from Laboratory of Economics and Management (LEM), Sant'Anna School of Advanced Studies, Pisa, Italy

Abstract: As artificial intelligence increasingly drives critical decisions, the ability to genuinely explain how neural networks make predictions is essential for trust. Yet, most current explanation methods offer post-hoc rationalizations rather than guaranteeing a true reflection of the model's reasoning. We introduce the notion of explanatory alignment, a requirement that explanations directly construct predictions rather than rationalize them. To achieve this in complex data domains, we present Pointwise-interpretable Networks (PiNets), a pseudo-linear architecture that forms linear models instance-wise. Evaluated on image classification and segmentation tasks, PiNets demonstrate that their explanations are deeply faithful across four criteria: meaningfulness, alignment, robustness, and sufficiency (MARS). Our contributions pave the way for promising avenues: by reconciling the predictive power of deep learning with the interpretability of linear models, PiNets provide a principled foundation for trustworthy AI and data-driven scientific discovery.

Keywords: Statistical modeling; Deep learning; Explainability; Pseudo-linear models (search for similar items in EconPapers)
Date: 2026-05-13
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.lem.sssup.it/WPLem/files/2026-15.pdf (application/pdf)
Our link check indicates that this URL is bad, the error code is: 500 Can't connect to www.lem.santannapisa.it:443 (certificate verify failed) (http://www.lem.sssup.it/WPLem/files/2026-15.pdf [302 Found]--> https://www.lem.santannapisa.it/WPLem/files/2026-15.pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ssa:lemwps:2026/15

Access Statistics for this paper

More papers in LEM Papers Series from Laboratory of Economics and Management (LEM), Sant'Anna School of Advanced Studies, Pisa, Italy Contact information at EDIRC.
Bibliographic data for series maintained by ().