# Rethinking Explanation Evaluation under the Retraining Scheme

arXiv: https://arxiv.org/abs/2511.08281 · HTML: https://mlsanity.com/paper/2511.08281/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (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)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [On the (In)fidelity and Sensitivity for Explanations](https://mlsanity.com/paper/1901.09392/) (2019)
- [Evaluating and Aggregating Feature-based Model Explanations](https://mlsanity.com/paper/2005.00631/) (2020)
- [A Consistent and Efficient Evaluation Strategy for Attribution Methods](https://mlsanity.com/paper/2202.00449/) (2022)
- [Missingness Bias in Model Debugging](https://mlsanity.com/paper/2204.08945/) (2022)
- [The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus](https://mlsanity.com/paper/2302.07265/) (2023)
- [Feature Perturbation Augmentation for Reliable Evaluation of Importance Estimators in Neural Networks](https://mlsanity.com/paper/2303.01538/) (2023)
- [Saliency strikes back: How filtering out high frequencies improves white-box explanations](https://mlsanity.com/paper/2307.09591/) (2023)
- [Geometric Remove-and-Retrain (GOAR): Coordinate-Invariant eXplainable AI Assessment](https://mlsanity.com/paper/2407.12401/) (2024)
- [On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box](https://mlsanity.com/paper/2308.09381/) (2023)

## Built on by (most cited first, 1 of 1)

- [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)

Feature attribution has gained prominence as a tool for explaining model decisions, yet evaluating explanation quality remains challenging due to the absence of ground-truth explanations. To circumvent this, explanation-guided input manipulation has emerged as an indirect evaluation strategy, measuring explanation effectiveness through the impact of input modifications on model outcomes during inference. Despite the widespread use, a major concern with inference-based schemes is the distribution shift caused by such manipulations, which undermines the reliability of their assessments. The retraining-based scheme ROAR overcomes this issue by adapting the model to the altered data distribution. However, its evaluation results often contradict the theoretical foundations of widely accepted explainers. This work investigates this misalignment between empirical observations and theoretical expectations. In particular, we identify the sign issue as a key factor responsible for residual information that ultimately distorts retraining-based evaluation. Based on the analysis, we show that a straightforward reframing of the evaluation process can effectively resolve the identified issue. Building on the existing framework, we further propose novel variants that jointly structure a comprehensive perspective on explanation evaluation. These variants largely improve evaluation efficiency over the standard retraining protocol, thereby enhancing practical applicability for explainer selection and benchmarking. Following our proposed schemes, empirical results across various data scales provide deeper insights into the performance of carefully selected explainers, revealing open challenges and future directions in explainability research.