# A Typology for Exploring the Mitigation of Shortcut Behavior

arXiv: https://arxiv.org/abs/2203.03668 · HTML: https://mlsanity.com/paper/2203.03668/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 45 references that are in the map.
- First posted on arXiv 4 Mar 2022.

## Builds on (most cited first, 27 of 27)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [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)
- [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)
- [Analysis Methods in Neural Language Processing: A Survey](https://mlsanity.com/paper/1812.08951/) (2018)
- [BCN20000: Dermoscopic Lesions in the Wild](https://mlsanity.com/paper/1908.02288/) (2019)
- [Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1605.01397/) (2016)
- [A Diagnostic Study of Explainability Techniques for Text Classification](https://mlsanity.com/paper/2009.13295/) (2020)
- [The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective](https://mlsanity.com/paper/2202.01602/) (2022)
- [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)
- [Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded](https://mlsanity.com/paper/1902.03751/) (2019)
- [Explaining in Style: Training a GAN to explain a classifier in StyleSpace](https://mlsanity.com/paper/2104.13369/) (2021)
- [Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations](https://mlsanity.com/paper/2011.12854/) (2020)
- [Interpretation of Prediction Models Using the Input Gradient](https://mlsanity.com/paper/1611.07634/) (2016)
- [Machine Guides, Human Supervises: Interactive Learning with Global Explanations](https://mlsanity.com/paper/2009.09723/) (2020)
- [Finding and Removing Clever Hans: Using Explanation Methods to Debug and Improve Deep Models](https://mlsanity.com/paper/1912.11425/) (2019)
- [Enlightening Deep Neural Networks with Knowledge of Confounding Factors](https://mlsanity.com/paper/1607.02397/) (2016)

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

- [Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness](https://mlsanity.com/paper/2302.10893/) (2023)
- [Revision Transformers: Instructing Language Models to Change their Values](https://mlsanity.com/paper/2210.10332/) (2022)
- [ILLUME: Rationalizing Vision-Language Models through Human Interactions](https://mlsanity.com/paper/2208.08241/) (2022)
- [Iterative Graph Neural Network Enhancement via Frequent Subgraph Mining of Explanations](https://mlsanity.com/paper/2403.07849/) (2024)
- [Increasing Performance And Sample Efficiency With Model-agnostic Interactive Feature Attributions](https://mlsanity.com/paper/2306.16431/) (2023)
- [Distance-Aware eXplanation Based Learning](https://mlsanity.com/paper/2309.05548/) (2023)
- [Trust Me, I Know the Way: Predictive Uncertainty in the Presence of Shortcut Learning](https://mlsanity.com/paper/2502.09137/) (2025)

## Abstract (arXiv)

As machine learning models become increasingly larger, trained weakly supervised on large, possibly uncurated data sets, it becomes increasingly important to establish mechanisms for inspecting, interacting, and revising models to mitigate learning shortcuts and guarantee their learned knowledge is aligned with human knowledge. The recently proposed XIL framework was developed for this purpose, and several such methods have been introduced, each with individual motivations and methodological details. In this work, we provide a unification of various XIL methods into a single typology by establishing a common set of basic modules. In doing so, we pave the way for a principled comparison of existing, but, importantly, also future XIL approaches. In addition, we discuss existing and introduce novel measures and benchmarks for evaluating the overall abilities of a XIL method. Given this extensive toolbox, including our typology, measures, and benchmarks, we finally compare several recent XIL methods methodologically and quantitatively. In our evaluations, all methods prove to revise a model successfully. However, we found remarkable differences in individual benchmark tasks, revealing valuable application-relevant aspects for integrating these benchmarks in developing future methods.