# A comprehensive study on fidelity metrics for XAI

arXiv: https://arxiv.org/abs/2401.10640 · HTML: https://mlsanity.com/paper/2401.10640/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 19 Jan 2024.

## Builds on (most cited first, 20 of 20)

- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [Methods for Interpreting and Understanding Deep Neural Networks](https://mlsanity.com/paper/1706.07979/) (2017)
- [On the (In)fidelity and Sensitivity for Explanations](https://mlsanity.com/paper/1901.09392/) (2019)
- [COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Images](https://mlsanity.com/paper/2003.09871/) (2020)
- [Evaluating and Aggregating Feature-based Model Explanations](https://mlsanity.com/paper/2005.00631/) (2020)
- [Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond](https://mlsanity.com/paper/2202.06861/) (2022)
- [The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective](https://mlsanity.com/paper/2202.01602/) (2022)
- [Explainable artificial intelligence (XAI) in deep learning-based medical image analysis](https://mlsanity.com/paper/2107.10912/) (2021)
- [Sanity Checks for Saliency Metrics](https://mlsanity.com/paper/1912.01451/) (2019)
- [IROF: a low resource evaluation metric for explanation methods](https://mlsanity.com/paper/2003.08747/) (2020)
- [Metrics for saliency map evaluation of deep learning explanation methods](https://mlsanity.com/paper/2201.13291/) (2022)
- [The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus](https://mlsanity.com/paper/2302.07265/) (2023)
- [Testing the robustness of attribution methods for convolutional neural networks in MRI-based Alzheimer's disease classification](https://mlsanity.com/paper/1909.08856/) (2019)
- [A novel approach to generate datasets with XAI ground truth to evaluate image models](https://mlsanity.com/paper/2302.05624/) (2023)

## Built on by (most cited first, 16 of 16)

- [FaithLM: Towards Faithful Explanations for Large Language Models](https://mlsanity.com/paper/2402.04678/) (2024)
- [Explainability in Practice: A Survey of Explainable NLP Across Various Domains](https://mlsanity.com/paper/2502.00837/) (2025)
- [Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics](https://mlsanity.com/paper/2403.18136/) (2024)
- [IBO: Inpainting-Based Occlusion to Enhance Explainable Artificial Intelligence Evaluation in Histopathology](https://mlsanity.com/paper/2408.16395/) (2024)
- [Meta-evaluating stability measures: MAX-Senstivity & AVG-Sensitivity](https://mlsanity.com/paper/2412.10942/) (2024)
- [Exploring SAIG Methods for an Objective Evaluation of XAI](https://mlsanity.com/paper/2602.08715/) (2026)
- [Upside-Down Reinforcement Learning for More Interpretable Optimal Control](https://mlsanity.com/paper/2411.11457/) (2024)
- [Multi-criteria Rank-based Aggregation for Explainable AI](https://mlsanity.com/paper/2505.24612/) (2025)
- [Attribution Upsampling should Redistribute, Not Interpolate](https://mlsanity.com/paper/2603.16067/) (2026)
- [AGRI-Fidelity: Evaluating the Reliability of Listenable Explanations for Poultry Disease Detection](https://mlsanity.com/paper/2603.18247/) (2026)
- [XAI-Grounded Explanation Generation for Speech Deepfake Detection with Training-Free Multimodal Large Language Models](https://mlsanity.com/paper/2606.16137/) (2026)
- [Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability](https://mlsanity.com/paper/2608.02238/) (2026)
- [Evaluating Explanation Methods by the Predictors They Induce](https://mlsanity.com/paper/2609.20058/) (2026)
- [A Synthetic Ground-Truth Framework for the Evaluation of Explainable AI Methods](https://mlsanity.com/paper/2609.30397/) (2026)
- [Beyond Trained Models: Compiling GNNs for a Sound Explainer Benchmark](https://mlsanity.com/paper/2610.03526/) (2026)
- [Faithfulness Without Anchors: A Position Paper on the Structural Misalignments of Explainable AI Faithfulness Metrics for Feature Importance](https://mlsanity.com/paper/2610.12493/) (2026)

## Abstract (arXiv)

The use of eXplainable Artificial Intelligence (XAI) systems has introduced a set of challenges that need resolution. Herein, we focus on how to correctly select an XAI method, an open questions within the field. The inherent difficulty of this task is due to the lack of a ground truth. Several authors have proposed metrics to approximate the fidelity of different XAI methods. These metrics lack verification and have concerning disagreements. In this study, we proposed a novel methodology to verify fidelity metrics, using a well-known transparent model, namely a decision tree. This model allowed us to obtain explanations with perfect fidelity. Our proposal constitutes the first objective benchmark for these metrics, facilitating a comparison of existing proposals, and surpassing existing methods. We applied our benchmark to assess the existing fidelity metrics in two different experiments, each using public datasets comprising 52,000 images. The images from these datasets had a size a 128 by 128 pixels and were synthetic data that simplified the training process. All metric values, indicated a lack of fidelity, with the best one showing a 30 % deviation from the expected values for perfect explanation. Our experimentation led us to conclude that the current fidelity metrics are not reliable enough to be used in real scenarios. From this finding, we deemed it necessary to development new metrics, to avoid the detected problems, and we recommend the usage of our proposal as a benchmark within the scientific community to address these limitations.