# The Disagreement Problem in Faithfulness Metrics

arXiv: https://arxiv.org/abs/2311.07763 · HTML: https://mlsanity.com/paper/2311.07763/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 13 Nov 2023.

## Builds on (most cited first, 19 of 19)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [Explaining by Removing: A Unified Framework for Model Explanation](https://mlsanity.com/paper/2011.14878/) (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)
- [Scaling Laws and Interpretability of Learning from Repeated Data](https://mlsanity.com/paper/2205.10487/) (2022)
- [OpenXAI: Towards a Transparent Evaluation of Model Explanations](https://mlsanity.com/paper/2206.11104/) (2022)
- [Unrestricted Permutation forces Extrapolation: Variable Importance Requires at least One More Model, or There Is No Free Variable Importance](https://mlsanity.com/paper/1905.03151/) (2019)
- [The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification](https://mlsanity.com/paper/1503.01161/) (2015)
- [Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations](https://mlsanity.com/paper/2205.07277/) (2022)
- [On Baselines for Local Feature Attributions](https://mlsanity.com/paper/2101.00905/) (2021)
- [Counterfactual Shapley Additive Explanations](https://mlsanity.com/paper/2110.14270/) (2021)
- [Statistical Analysis and Parameter Selection for Mapper](https://mlsanity.com/paper/1706.00204/) (2017)
- [BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligence](https://mlsanity.com/paper/2207.05566/) (2022)

## Built on by (most cited first, 6 of 6)

- [Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks](https://mlsanity.com/paper/2401.06654/) (2024)
- [Evaluating Model Explanations without Ground Truth](https://mlsanity.com/paper/2505.10399/) (2025)
- [Beyond the Single-Best Model: Rashomon Partial Dependence Profile for Trustworthy Explanations in AutoML](https://mlsanity.com/paper/2507.14744/) (2025)
- [A Sim2Real Approach for Identifying Task-Relevant Properties in Interpretable Machine Learning](https://mlsanity.com/paper/2406.00116/) (2024)
- [Additive Large Language Models for Semi-Structured Text](https://mlsanity.com/paper/2511.11922/) (2025)
- [Attribution Upsampling should Redistribute, Not Interpolate](https://mlsanity.com/paper/2603.16067/) (2026)

## Abstract (arXiv)

The field of explainable artificial intelligence (XAI) aims to explain how black-box machine learning models work. Much of the work centers around the holy grail of providing post-hoc feature attributions to any model architecture. While the pace of innovation around novel methods has slowed down, the question remains of how to choose a method, and how to make it fit for purpose. Recently, efforts around benchmarking XAI methods have suggested metrics for that purpose -- but there are many choices. That bounty of choice still leaves an end user unclear on how to proceed. This paper focuses on comparing metrics with the aim of measuring faithfulness of local explanations on tabular classification problems -- and shows that the current metrics don't agree; leaving users unsure how to choose the most faithful explanations.