# Evaluating Model Explanations without Ground Truth

arXiv: https://arxiv.org/abs/2505.10399 · HTML: https://mlsanity.com/paper/2505.10399/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 58 references that are in the map.
- First posted on arXiv 15 May 2025.

## Builds on (most cited first, 30 of 33)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [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)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Understanding Deep Networks via Extremal Perturbations and Smooth Masks](https://mlsanity.com/paper/1910.08485/) (2019)
- [Manipulating and Measuring Model Interpretability](https://mlsanity.com/paper/1802.07810/) (2018)
- [Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?](https://mlsanity.com/paper/2005.01831/) (2020)
- [Predictive Multiplicity in Classification](https://mlsanity.com/paper/1909.06677/) (2019)
- [Learning Model-Agnostic Counterfactual Explanations for Tabular Data](https://mlsanity.com/paper/1910.09398/) (2019)
- [Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systems](https://mlsanity.com/paper/2001.08298/) (2020)
- [Human-Centered Explainable AI (XAI): From Algorithms to User Experiences](https://mlsanity.com/paper/2110.10790/) (2021)
- [Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges](https://mlsanity.com/paper/2010.09337/) (2020)
- [XRAI: Better Attributions Through Regions](https://mlsanity.com/paper/1906.02825/) (2019)
- [What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods](https://mlsanity.com/paper/2112.04417/) (2021)
- [Evaluating Saliency Map Explanations for Convolutional Neural Networks: A User Study](https://mlsanity.com/paper/2002.00772/) (2020)
- [Synthetic Benchmarks for Scientific Research in Explainable Machine Learning](https://mlsanity.com/paper/2106.12543/) (2021)
- [Do Explanations make VQA Models more Predictable to a Human?](https://mlsanity.com/paper/1810.12366/) (2018)
- [Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations](https://mlsanity.com/paper/2205.07277/) (2022)
- [Machine Explanations and Human Understanding](https://mlsanity.com/paper/2202.04092/) (2022)
- [Stability of clinical prediction models developed using statistical or machine learning methods](https://mlsanity.com/paper/2211.01061/) (2022)

## Built on by (most cited first, 7 of 7)

- [Variance-Bounded Evaluation of Entity-Centric AI Systems Without Ground Truth: Theory and Measurement](https://mlsanity.com/paper/2509.22751/) (2025)
- [xaitimesynth: A Python Package for Evaluating Attribution Methods for Time Series with Synthetic Ground Truth](https://mlsanity.com/paper/2603.06781/) (2026)
- [Implicit Hypothesis Testing and Divergence Preservation in Neural Network Representations](https://mlsanity.com/paper/2601.20477/) (2026)
- [Does Explanation Correctness Matter? Linking Computational XAI Evaluation to Human Understanding](https://mlsanity.com/paper/2603.25251/) (2026)
- [Stabilising Explainability Fragility in Cybersecurity AI: The Impact and Mitigation of Multicollinearity in Public Benchmark Datasets](https://mlsanity.com/paper/2605.22529/) (2026)
- [FMMO: Detecting the Divergence Between Local Attribution and Global Drift](https://mlsanity.com/paper/2609.06173/) (2026)
- [MEA: A Reward-Driven Multi-Agent System for Faithful Model Explanations](https://mlsanity.com/paper/2610.02480/) (2026)

## Abstract (arXiv)

There can be many competing and contradictory explanations for a single model prediction, making it difficult to select which one to use. Current explanation evaluation frameworks measure quality by comparing against ideal "ground-truth" explanations, or by verifying model sensitivity to important inputs. We outline the limitations of these approaches, and propose three desirable principles to ground the future development of explanation evaluation strategies for local feature importance explanations. We propose a ground-truth Agnostic eXplanation Evaluation framework (AXE) for evaluating and comparing model explanations that satisfies these principles. Unlike prior approaches, AXE does not require access to ideal ground-truth explanations for comparison, or rely on model sensitivity - providing an independent measure of explanation quality. We verify AXE by comparing with baselines, and show how it can be used to detect explanation fairwashing. Our code is available at https://github.com/KaiRawal/Evaluating-Model-Explanations-without-Ground-Truth.