XAI-Units: Benchmarking Explainability Methods with Unit Tests

• URL: http://arxiv.org/abs/2506.01059v1
• Date: Sun, 01 Jun 2025 15:58:27 GMT
• Title: XAI-Units: Benchmarking Explainability Methods with Unit Tests
• Abstract summary: Feature attribution methods are widely used in explainable AI (XAI)<n>Different FA models often provide disagreeing importance scores for the same model.<n>We introduce the open-source XAI-Units benchmark to evaluate FA methods against diverse types of model behaviours.
• Score: 8.169313776845344
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Feature attribution (FA) methods are widely used in explainable AI (XAI) to help users understand how the inputs of a machine learning model contribute to its outputs. However, different FA models often provide disagreeing importance scores for the same model. In the absence of ground truth or in-depth knowledge about the inner workings of the model, it is often difficult to meaningfully determine which of the different FA methods produce more suitable explanations in different contexts. As a step towards addressing this issue, we introduce the open-source XAI-Units benchmark, specifically designed to evaluate FA methods against diverse types of model behaviours, such as feature interactions, cancellations, and discontinuous outputs. Our benchmark provides a set of paired datasets and models with known internal mechanisms, establishing clear expectations for desirable attribution scores. Accompanied by a suite of built-in evaluation metrics, XAI-Units streamlines systematic experimentation and reveals how FA methods perform against distinct, atomic kinds of model reasoning, similar to unit tests in software engineering. Crucially, by using procedurally generated models tied to synthetic datasets, we pave the way towards an objective and reliable comparison of FA methods.

Related papers

• Learning Quantifiable Visual Explanations Without Ground-Truth [13.453747733500506]
  We propose a framework that serves as a quantifiable metric for the quality of XAI methods.<n>We also propose a novel XAI method, considering the case where we fine-tune a model using a differentiable approximation of the metric.<n>We show that the explanations generated by this method outperform those of competing XAI techniques according to a number of quantifiable metrics.
  arXiv  Detail & Related papers  (2026-05-18T17:21:48Z)
• From Confusion to Clarity: ProtoScore - A Framework for Evaluating Prototype-Based XAI [2.9583904454291168]
  We establish a robust framework, ProtoScore, for assessing prototype-based XAI methods across different data types.<n>By integrating the Co-12 properties of Nauta et al., this framework allows for effectively comparing prototype methods against each other and against other XAI methods.
  arXiv  Detail & Related papers  (2025-11-11T15:38:29Z)
• Nonparametric Data Attribution for Diffusion Models [57.820618036556084]
  Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs.<n>We propose a nonparametric attribution method that operates entirely on data, measuring influence via patch-level similarity between generated and training images.
  arXiv  Detail & Related papers  (2025-10-16T03:37:16Z)
• Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check [60.77691669644931]
  We propose Functional Alignment for Distributional Equivalence (FADE), a novel metric that measures distributional similarity between unlearned and reference models.<n>We show that FADE captures functional alignment across the entire output distribution, providing a principled assessment of genuine unlearning.<n>These findings expose fundamental gaps in current evaluation practices and demonstrate that FADE provides a more robust foundation for developing and assessing truly effective unlearning methods.
  arXiv  Detail & Related papers  (2025-10-14T20:50:30Z)
• A Comparative Study of Explainable AI Methods: Model-Agnostic vs. Model-Specific Approaches [0.0]
  I examine how LIME and SHAP differ from Grad-CAM and Guided Backpropagation when interpreting ResNet50 predictions.<n>I found that each method reveals different aspects of the models decision-making process.<n>My analysis shows there is no "one-size-fits-all" solution for model interpretability.
  arXiv  Detail & Related papers  (2025-04-05T20:13:20Z)
• Unified Explanations in Machine Learning Models: A Perturbation Approach [0.0]
  Inconsistencies between XAI and modeling techniques can have the undesirable effect of casting doubt upon the efficacy of these explainability approaches. We propose a systematic, perturbation-based analysis against a popular, model-agnostic method in XAI, SHapley Additive exPlanations (Shap) We devise algorithms to generate relative feature importance in settings of dynamic inference amongst a suite of popular machine learning and deep learning methods, and metrics that allow us to quantify how well explanations generated under the static case hold.
  arXiv  Detail & Related papers  (2024-05-30T16:04:35Z)
• EXACT: Towards a platform for empirically benchmarking Machine Learning model explanation methods [1.6383837447674294]
  This paper brings together various benchmark datasets and novel performance metrics in an initial benchmarking platform. Our datasets incorporate ground truth explanations for class-conditional features. This platform assesses the performance of post-hoc XAI methods in the quality of the explanations they produce.
  arXiv  Detail & Related papers  (2024-05-20T14:16:06Z)
• Explanation-by-Example Based on Item Response Theory [0.0]
  This research explores the Item Response Theory (IRT) as a tool to explaining the models and measuring the level of reliability of the Explanation-by-Example approach. From the test set, 83.8% of the errors are from instances in which the IRT points out the model as unreliable.
  arXiv  Detail & Related papers  (2022-10-04T14:36:33Z)
• MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation [132.77005365032468]
  We propose a novel framework of Model-Agnostic Counterfactual Explanation (MACE) In our MACE approach, we propose a novel RL-based method for finding good counterfactual examples and a gradient-less descent method for improving proximity. Experiments on public datasets validate the effectiveness with better validity, sparsity and proximity.
  arXiv  Detail & Related papers  (2022-05-31T04:57:06Z)
• Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement [75.00655434905417]
  Explainable Artificial Intelligence (XAI) is an emerging research field bringing transparency to highly complex machine learning (ML) models. This paper offers a comprehensive overview over techniques that apply XAI practically for improving various properties of ML models. We show empirically through experiments on toy and realistic settings how explanations can help improve properties such as model generalization ability or reasoning.
  arXiv  Detail & Related papers  (2022-03-15T15:44:28Z)
• Model-agnostic multi-objective approach for the evolutionary discovery of mathematical models [55.41644538483948]
  In modern data science, it is more interesting to understand the properties of the model, which parts could be replaced to obtain better results. We use multi-objective evolutionary optimization for composite data-driven model learning to obtain the algorithm's desired properties.
  arXiv  Detail & Related papers  (2021-07-07T11:17:09Z)
• Interpretable Multi-dataset Evaluation for Named Entity Recognition [110.64368106131062]
  We present a general methodology for interpretable evaluation for the named entity recognition (NER) task. The proposed evaluation method enables us to interpret the differences in models and datasets, as well as the interplay between them. By making our analysis tool available, we make it easy for future researchers to run similar analyses and drive progress in this area.
  arXiv  Detail & Related papers  (2020-11-13T10:53:27Z)
• A Diagnostic Study of Explainability Techniques for Text Classification [52.879658637466605]
  We develop a list of diagnostic properties for evaluating existing explainability techniques. We compare the saliency scores assigned by the explainability techniques with human annotations of salient input regions to find relations between a model's performance and the agreement of its rationales with human ones.
  arXiv  Detail & Related papers  (2020-09-25T12:01:53Z)
• Evaluating the Disentanglement of Deep Generative Models through Manifold Topology [66.06153115971732]
  We present a method for quantifying disentanglement that only uses the generative model. We empirically evaluate several state-of-the-art models across multiple datasets.
  arXiv  Detail & Related papers  (2020-06-05T20:54:11Z)

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.