Skip to main navigation Skip to search Skip to main content

On the Relationship Between Neural Gradients and Model Reasoning

  • Jéssica Richards*
  • , Carlos Eduardo Pedreira
  • , Elizabeth Fialho Wanner
  • , Carolina Gil Marcelino
  • *Corresponding author for this work
  • Universidade Federal do Rio de Janeiro

Research output: Chapter in Book/Published conference outputConference publication

Abstract

As machine learning increasingly shapes decisions that directly impact people’s lives, the demand for transparency and accountability has grown. Explainable Artificial Intelligence (XAI) has emerged as a field dedicated to making the reasoning of autonomous decision systems clearer and more interpretable. Among the many approaches to XAI, gradient-based explanations use a model’s internal gradients to highlight feature importance. In this work, we investigate whether a model’s gradients reveal consistent patterns that reflect its reasoning process. To keep the problem tractable, given the exponential growth in neural network dimensionality and corresponding gradients, we conducted our experiments using a Multilayer Perceptron as a controlled, toy example. For statistical analysis, we applied the Mantel and Energy tests. Our results indicate that gradient patterns emerge as intrinsic properties of the model’s architecture and the dataset on which it is trained.

Original languageEnglish
Title of host publicationFrom Data to Models and Back: 13th International Symposium, DataMod 2025, Toledo, Spain, November 10–11, 2025, Revised Selected Papers
EditorsLivia Lestingi, Gwen Salaün, José Ignacio Requeno Jarabo
PublisherSpringer, Cham
Pages119-126
Number of pages8
Volume16421
ISBN (Electronic)9783032255525
ISBN (Print)9783032255518
DOIs
Publication statusPublished - 2 Jul 2026
Event13th International Symposium on From Data Models and Back, DataMod 2025 - Toledo, Spain
Duration: 10 Nov 202511 Nov 2025

Publication series

NameLecture Notes in Computer Science (LNCS)
Volume16421
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference13th International Symposium on From Data Models and Back, DataMod 2025
Country/TerritorySpain
CityToledo
Period10/11/2511/11/25

Bibliographical note

Copyright © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. This version of the article has been accepted for publication, after peer review and is subject to Springer Nature’s AM terms of use [ https://www.springernature.com/gp/open-research/policies/accepted-manuscript-terms ] but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-032-25552-5_8

Keywords

  • Explainable Artificial Intelligence
  • Gradients
  • Multilayer Perceptron

Fingerprint

Dive into the research topics of 'On the Relationship Between Neural Gradients and Model Reasoning'. Together they form a unique fingerprint.

Cite this