# Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models arXiv: https://arxiv.org/abs/2303.12641 ยท HTML: https://mlsanity.com/paper/2303.12641/ ## Key facts - Cited by 17 papers in the map (data through 14 Oct 2026). - Builds on 12 of its 24 references that are in the map. - First posted on arXiv 22 Mar 2023. ## Builds on (most cited first, 12 of 12) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014) - [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019) - [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017) - [Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1710.05006/) (2017) - [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019) - [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017) - [Learning Not to Learn: Training Deep Neural Networks with Biased Data](https://mlsanity.com/paper/1812.10352/) (2018) - [Interpretations are useful: penalizing explanations to align neural networks with prior knowledge](https://mlsanity.com/paper/1909.13584/) (2019) - [Making deep neural networks right for the right scientific reasons by interacting with their explanations](https://mlsanity.com/paper/2001.05371/) (2020) - [Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs](https://mlsanity.com/paper/1801.05453/) (2018) - [Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement](https://mlsanity.com/paper/2203.08008/) (2022) ## Built on by (most cited first, 17 of 17) - [Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions](https://mlsanity.com/paper/2310.19775/) (2023) - [LLMs for Explainable AI: A Comprehensive Survey](https://mlsanity.com/paper/2504.00125/) (2025) - [Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation](https://mlsanity.com/paper/2312.14223/) (2023) - [Mechanistic understanding and validation of large AI models with SemanticLens](https://mlsanity.com/paper/2501.05398/) (2025) - [Interpreting and Correcting Medical Image Classification with PIP-Net](https://mlsanity.com/paper/2307.10404/) (2023) - [Controllable Continual Test-Time Adaptation](https://mlsanity.com/paper/2405.14602/) (2024) - [Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression](https://mlsanity.com/paper/2404.09601/) (2024) - [Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts](https://mlsanity.com/paper/2303.17595/) (2023) - [Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs](https://mlsanity.com/paper/2506.13727/) (2025) - [The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis](https://mlsanity.com/paper/2408.02379/) (2024) - [Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data](https://mlsanity.com/paper/2501.13818/) (2025) - [A Survey on Interpretability in Visual Recognition](https://mlsanity.com/paper/2507.11099/) (2025) - [Post-Hoc Concept Disentanglement: From Correlated to Isolated Concept Representations](https://mlsanity.com/paper/2503.05522/) (2025) - [Towards Facilitated Fairness Assessment of AI-based Skin Lesion Classifiers Through GenAI-based Image Synthesis](https://mlsanity.com/paper/2507.17860/) (2025) - [Attribution Graphs and Causal Probing for Mechanistic Discovery and Bias Repair in Multimodal Generative Learning](https://mlsanity.com/paper/2510.12957/) (2025) - [ICON decomposition: Multivariate concept auditing reveals shortcuts that neural networks rely on](https://mlsanity.com/paper/2608.26083/) (2026) - [MedDiME: Efficient Latent Diffusion with Adaptive Masking for Medical Counterfactual Generation](https://mlsanity.com/paper/2609.15647/) (2026) ## Abstract (arXiv) State-of-the-art machine learning models often learn spurious correlations embedded in the training data. This poses risks when deploying these models for high-stake decision-making, such as in medical applications like skin cancer detection. To tackle this problem, we propose Reveal to Revise (R2R), a framework entailing the entire eXplainable Artificial Intelligence (XAI) life cycle, enabling practitioners to iteratively identify, mitigate, and (re-)evaluate spurious model behavior with a minimal amount of human interaction. In the first step (1), R2R reveals model weaknesses by finding outliers in attributions or through inspection of latent concepts learned by the model. Secondly (2), the responsible artifacts are detected and spatially localized in the input data, which is then leveraged to (3) revise the model behavior. Concretely, we apply the methods of RRR, CDEP and ClArC for model correction, and (4) (re-)evaluate the model's performance and remaining sensitivity towards the artifact. Using two medical benchmark datasets for Melanoma detection and bone age estimation, we apply our R2R framework to VGG, ResNet and EfficientNet architectures and thereby reveal and correct real dataset-intrinsic artifacts, as well as synthetic variants in a controlled setting. Completing the XAI life cycle, we demonstrate multiple R2R iterations to mitigate different biases. Code is available on https://github.com/maxdreyer/Reveal2Revise.