# On quantitative aspects of model interpretability

arXiv: https://arxiv.org/abs/2007.07584 · HTML: https://mlsanity.com/paper/2007.07584/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2020.

## Built on by (most cited first, 30 of 71)

- [Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond](https://mlsanity.com/paper/2202.06861/) (2022)
- [A Consistent and Efficient Evaluation Strategy for Attribution Methods](https://mlsanity.com/paper/2202.00449/) (2022)
- [Synthetic Benchmarks for Scientific Research in Explainable Machine Learning](https://mlsanity.com/paper/2106.12543/) (2021)
- [Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks](https://mlsanity.com/paper/2212.05946/) (2022)
- [The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus](https://mlsanity.com/paper/2302.07265/) (2023)
- [NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weights](https://mlsanity.com/paper/2106.10185/) (2021)
- [Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science](https://mlsanity.com/paper/2303.00652/) (2023)
- [Towards Evaluating Explanations of Vision Transformers for Medical Imaging](https://mlsanity.com/paper/2304.06133/) (2023)
- [What Makes a Good Explanation?: A Harmonized View of Properties of Explanations](https://mlsanity.com/paper/2211.05667/) (2022)
- [Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations](https://mlsanity.com/paper/2211.12486/) (2022)
- [Scrutinizing XAI using linear ground-truth data with suppressor variables](https://mlsanity.com/paper/2111.07473/) (2021)
- [Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks](https://mlsanity.com/paper/2410.02331/) (2024)
- [Evaluating the Explainers: Black-Box Explainable Machine Learning for Student Success Prediction in MOOCs](https://mlsanity.com/paper/2207.00551/) (2022)
- [An Objective Metric for Explainable AI: How and Why to Estimate the Degree of Explainability](https://mlsanity.com/paper/2109.05327/) (2021)
- [Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics](https://mlsanity.com/paper/2409.16756/) (2024)
- [Global Counterfactual Directions](https://mlsanity.com/paper/2404.12488/) (2024)
- [Hierarchical Label-wise Attention Transformer Model for Explainable ICD Coding](https://mlsanity.com/paper/2204.10716/) (2022)
- [RELAX: Representation Learning Explainability](https://mlsanity.com/paper/2112.10161/) (2021)
- [Explainability of Vision Transformers: A Comprehensive Review and New Perspectives](https://mlsanity.com/paper/2311.06786/) (2023)
- [Establishing and Evaluating Trustworthy AI: Overview and Research Challenges](https://mlsanity.com/paper/2411.09973/) (2024)
- [Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools](https://mlsanity.com/paper/2108.13961/) (2021)
- [Unlocking the Black Box: Analysing the EU Artificial Intelligence Act's Framework for Explainability in AI](https://mlsanity.com/paper/2502.14868/) (2025)
- [Why Should I Choose You? AutoXAI: A Framework for Selecting and Tuning eXplainable AI Solutions](https://mlsanity.com/paper/2210.02795/) (2022)
- [Feature Perturbation Augmentation for Reliable Evaluation of Importance Estimators in Neural Networks](https://mlsanity.com/paper/2303.01538/) (2023)
- [Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test](https://mlsanity.com/paper/2401.06465/) (2024)
- [A Survey on Methods and Metrics for the Assessment of Explainability under the Proposed AI Act](https://mlsanity.com/paper/2110.11168/) (2021)
- [A Fresh Look at Sanity Checks for Saliency Maps](https://mlsanity.com/paper/2405.02383/) (2024)
- [Benchmarking XAI Explanations with Human-Aligned Evaluations](https://mlsanity.com/paper/2411.02470/) (2024)
- [What Does Evaluation of Explainable Artificial Intelligence Actually Tell Us? A Case for Compositional and Contextual Validation of XAI Building Blocks](https://mlsanity.com/paper/2403.12730/) (2024)
- [Toward Understanding the Disagreement Problem in Neural Network Feature Attribution](https://mlsanity.com/paper/2404.11330/) (2024)

## Abstract (arXiv)

Despite the growing body of work in interpretable machine learning, it remains unclear how to evaluate different explainability methods without resorting to qualitative assessment and user-studies. While interpretability is an inherently subjective matter, previous works in cognitive science and epistemology have shown that good explanations do possess aspects that can be objectively judged apart from fidelity), such assimplicity and broadness. In this paper we propose a set of metrics to programmatically evaluate interpretability methods along these dimensions. In particular, we argue that the performance of methods along these dimensions can be orthogonally imputed to two conceptual parts, namely the feature extractor and the actual explainability method. We experimentally validate our metrics on different benchmark tasks and show how they can be used to guide a practitioner in the selection of the most appropriate method for the task at hand.