# xGEMs: Generating Examplars to Explain Black-Box Models

arXiv: https://arxiv.org/abs/1806.08867 · HTML: https://mlsanity.com/paper/1806.08867/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jun 2018.

## Built on by (most cited first, 21 of 21)

- [Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies](https://mlsanity.com/paper/2112.11471/) (2021)
- [Diffusion Models for Counterfactual Explanations](https://mlsanity.com/paper/2203.15636/) (2022)
- [Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations](https://mlsanity.com/paper/2103.10226/) (2021)
- [Adversarial Counterfactual Visual Explanations](https://mlsanity.com/paper/2303.09962/) (2023)
- [Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation](https://mlsanity.com/paper/2312.14223/) (2023)
- [Cycle-Consistent Counterfactuals by Latent Transformations](https://mlsanity.com/paper/2203.15064/) (2022)
- [Robust Feature-Level Adversaries are Interpretability Tools](https://mlsanity.com/paper/2110.03605/) (2021)
- [Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates](https://mlsanity.com/paper/2112.02646/) (2021)
- [Model-Based Counterfactual Synthesizer for Interpretation](https://mlsanity.com/paper/2106.08971/) (2021)
- [Efficient XAI Techniques: A Taxonomic Survey](https://mlsanity.com/paper/2302.03225/) (2023)
- [Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation](https://mlsanity.com/paper/2101.06930/) (2021)
- [Inherently Interpretable Multi-Label Classification Using Class-Specific Counterfactuals](https://mlsanity.com/paper/2303.00500/) (2023)
- [FASTER-CE: Fast, Sparse, Transparent, and Robust Counterfactual Explanations](https://mlsanity.com/paper/2210.06578/) (2022)
- [Diagnostics for Deep Neural Networks with Automated Copy/Paste Attacks](https://mlsanity.com/paper/2211.10024/) (2022)
- [δ-CLUE: Diverse Sets of Explanations for Uncertainty Estimates](https://mlsanity.com/paper/2104.06323/) (2021)
- [Gifsplanation via Latent Shift: A Simple Autoencoder Approach to Counterfactual Generation for Chest X-rays](https://mlsanity.com/paper/2102.09475/) (2021)
- [Outcome-Guided Counterfactuals for Reinforcement Learning Agents from a Jointly Trained Generative Latent Space](https://mlsanity.com/paper/2207.07710/) (2022)
- [Identifying Spurious Correlations using Counterfactual Alignment](https://mlsanity.com/paper/2312.02186/) (2023)
- [Explaining the Black-box Smoothly- A Counterfactual Approach](https://mlsanity.com/paper/2101.04230/) (2021)
- [Attri-Net: A Globally and Locally Inherently Interpretable Model for Multi-Label Classification Using Class-Specific Counterfactuals](https://mlsanity.com/paper/2406.05477/) (2024)
- [Comparison of Machine Learning Classification Algorithms and Application to the Framingham Heart Study](https://mlsanity.com/paper/2402.15005/) (2024)

## Abstract (arXiv)

This work proposes xGEMs or manifold guided exemplars, a framework to understand black-box classifier behavior by exploring the landscape of the underlying data manifold as data points cross decision boundaries. To do so, we train an unsupervised implicit generative model -- treated as a proxy to the data manifold. We summarize black-box model behavior quantitatively by perturbing data samples along the manifold. We demonstrate xGEMs' ability to detect and quantify bias in model learning and also for understanding the changes in model behavior as training progresses.