EvoXplain: When Machine Learning Models Agree on Predictions but Disagree on Why -- Measuring Mechanistic Multiplicity Across Training Runs

• URL: http://arxiv.org/abs/2512.22240v1
• Date: Tue, 23 Dec 2025 18:34:51 GMT
• Title: EvoXplain: When Machine Learning Models Agree on Predictions but Disagree on Why -- Measuring Mechanistic Multiplicity Across Training Runs
• Authors: Chama Bensmail,
• Abstract summary: We introduce EvoXplain, a diagnostic framework that measures the stability of model explanations across repeated training.<n>We evaluate EvoXplain on the Breast Cancer and COMPAS datasets using two widely deployed model classes: Logistic Regression and Random Forests.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine learning models are primarily judged by predictive performance, especially in applied settings. Once a model reaches high accuracy, its explanation is often assumed to be correct and trustworthy. However, this assumption raises an overlooked question: when two models achieve high accuracy, do they rely on the same internal logic, or do they reach the same outcome via different -- and potentially competing -- mechanisms? We introduce EvoXplain, a diagnostic framework that measures the stability of model explanations across repeated training. Rather than analysing a single trained model, EvoXplain treats explanations as samples drawn from the stochastic optimisation process itself -- without aggregating predictions or constructing ensembles -- and examines whether these samples form a single coherent explanation or separate into multiple, distinct explanatory modes. We evaluate EvoXplain on the Breast Cancer and COMPAS datasets using two widely deployed model classes: Logistic Regression and Random Forests. Although all models achieve high predictive accuracy, their explanations frequently exhibit clear multimodality. Even models commonly assumed to be stable, such as Logistic Regression, can produce multiple well-separated explanatory basins under repeated training on the same data split. These differences are not explained by hyperparameter variation or simple performance trade-offs. EvoXplain does not attempt to select a 'correct' explanation. Instead, it makes explanatory instability visible and quantifiable, revealing when single-instance or averaged explanations obscure the existence of multiple underlying mechanisms. More broadly, EvoXplain reframes interpretability as a property of a model class under repeated instantiation, rather than of any single trained model.

Related papers

• On Arbitrary Predictions from Equally Valid Models [49.56463611078044]
  Model multiplicity refers to multiple machine learning models that admit conflicting predictions for the same patient.<n>We show that even small ensembles can mitigate/eliminate predictive multiplicity in practice.
  arXiv  Detail & Related papers  (2025-07-25T16:15:59Z)
• Information-Theoretic Framework for Understanding Modern Machine-Learning [4.435094091999926]
  We present an information-theoretic framework that views learning as universal prediction under log loss.<n>We argue that successful architectures possess a broad complexity range, enabling learning in highly over- parameterized model classes.<n>The framework sheds light on the role of inductive biases, the effectiveness of descent gradient, and phenomena such as flat minima.
  arXiv  Detail & Related papers  (2025-06-09T11:32:31Z)
• Revisiting Optimism and Model Complexity in the Wake of Overparameterized Machine Learning [6.278498348219108]
  We revisit model complexity from first principles, by first reinterpreting and then extending the classical statistical concept of (effective) degrees of freedom. We demonstrate the utility of our proposed complexity measures through a mix of conceptual arguments, theory, and experiments.
  arXiv  Detail & Related papers  (2024-10-02T06:09:57Z)
• Interpretability in Symbolic Regression: a benchmark of Explanatory Methods using the Feynman data set [0.0]
  Interpretability of machine learning models plays a role as important as the model accuracy. This paper proposes a benchmark scheme to evaluate explanatory methods to explain regression models. Results have shown that Symbolic Regression models can be an interesting alternative to white-box and black-box models.
  arXiv  Detail & Related papers  (2024-04-08T23:46:59Z)
• Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations [64.85696493596821]
  In computer vision applications, generative counterfactual methods indicate how to perturb a model's input to change its prediction. We propose a counterfactual method that learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss. Our model improves the success rate of producing high-quality valuable explanations when compared to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-03-18T12:57:34Z)
• Why do classifier accuracies show linear trends under distribution shift? [58.40438263312526]
  accuracies of models on one data distribution are approximately linear functions of the accuracies on another distribution. We assume the probability that two models agree in their predictions is higher than what we can infer from their accuracy levels alone. We show that a linear trend must occur when evaluating models on two distributions unless the size of the distribution shift is large.
  arXiv  Detail & Related papers  (2020-12-31T07:24:30Z)
• A Note on High-Probability versus In-Expectation Guarantees of Generalization Bounds in Machine Learning [95.48744259567837]
  Statistical machine learning theory often tries to give generalization guarantees of machine learning models. Statements made about the performance of machine learning models have to take the sampling process into account. We show how one may transform one statement to another.
  arXiv  Detail & Related papers  (2020-10-06T09:41:35Z)
• Deducing neighborhoods of classes from a fitted model [68.8204255655161]
  In this article a new kind of interpretable machine learning method is presented. It can help to understand the partitioning of the feature space into predicted classes in a classification model using quantile shifts. Basically, real data points (or specific points of interest) are used and the changes of the prediction after slightly raising or decreasing specific features are observed.
  arXiv  Detail & Related papers  (2020-09-11T16:35:53Z)
• Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction [49.254162397086006]
  We study explanations based on visual saliency in an image-based age prediction task. We find that presenting model predictions improves human accuracy. However, explanations of various kinds fail to significantly alter human accuracy or trust in the model.
  arXiv  Detail & Related papers  (2020-07-23T20:39:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.