# Leveraging Latent Features for Local Explanations

arXiv: https://arxiv.org/abs/1905.12698 · HTML: https://mlsanity.com/paper/1905.12698/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2019.

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

- [Benchmarking and Survey of Explanation Methods for Black Box Models](https://mlsanity.com/paper/2102.13076/) (2021)
- [A Primer on Contrastive Pretraining in Language Processing: Methods, Lessons Learned and Perspectives](https://mlsanity.com/paper/2102.12982/) (2021)
- [DISSECT: Disentangled Simultaneous Explanations via Concept Traversals](https://mlsanity.com/paper/2105.15164/) (2021)
- [Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAI](https://mlsanity.com/paper/2301.11970/) (2023)
- [The Solvability of Interpretability Evaluation Metrics](https://mlsanity.com/paper/2205.08696/) (2022)
- [Let the CAT out of the bag: Contrastive Attributed explanations for Text](https://mlsanity.com/paper/2109.07983/) (2021)
- [AI Explainability 360: Impact and Design](https://mlsanity.com/paper/2109.12151/) (2021)
- [On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach](https://mlsanity.com/paper/2211.01498/) (2022)
- [Interpretable Mesomorphic Networks for Tabular Data](https://mlsanity.com/paper/2305.13072/) (2023)
- [Learning to Explain: Prototype-Based Surrogate Models for LLM Classification](https://mlsanity.com/paper/2505.18970/) (2025)
- [When Stability meets Sufficiency: Informative Explanations that do not Overwhelm](https://mlsanity.com/paper/2109.06181/) (2021)
- [Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners](https://mlsanity.com/paper/2202.01153/) (2022)
- [Explainable AI for clinical risk prediction: a survey of concepts, methods, and modalities](https://mlsanity.com/paper/2308.08407/) (2023)
- [FIND:Explainable Framework for Meta-learning](https://mlsanity.com/paper/2205.10362/) (2022)
- [Truthful Meta-Explanations for Local Interpretability of Machine Learning Models](https://mlsanity.com/paper/2212.03513/) (2022)
- [Evaluating Explainability in Machine Learning Predictions through Explainer-Agnostic Metrics](https://mlsanity.com/paper/2302.12094/) (2023)
- [Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanations](https://mlsanity.com/paper/2210.08902/) (2022)
- [Harmonizing Feature Attributions Across Deep Learning Architectures: Enhancing Interpretability and Consistency](https://mlsanity.com/paper/2307.02150/) (2023)
- [CELL your Model: Contrastive Explanations for Large Language Models](https://mlsanity.com/paper/2406.11785/) (2024)
- [AGRI-Fidelity: Evaluating the Reliability of Listenable Explanations for Poultry Disease Detection](https://mlsanity.com/paper/2603.18247/) (2026)
- [Explainable Control Framework (XCF) based on Fuzzy Model-Agnostic Explanation and LLM Agent-Supported Interface](https://mlsanity.com/paper/2606.25941/) (2026)

## Abstract (arXiv)

As the application of deep neural networks proliferates in numerous areas such as medical imaging, video surveillance, and self driving cars, the need for explaining the decisions of these models has become a hot research topic, both at the global and local level. Locally, most explanation methods have focused on identifying relevance of features, limiting the types of explanations possible. In this paper, we investigate a new direction by leveraging latent features to generate contrastive explanations; predictions are explained not only by highlighting aspects that are in themselves sufficient to justify the classification, but also by new aspects which if added will change the classification. The key contribution of this paper lies in how we add features to rich data in a formal yet humanly interpretable way that leads to meaningful results. Our new definition of "addition" uses latent features to move beyond the limitations of previous explanations and resolve an open question laid out in Dhurandhar, et. al. (2018), which creates local contrastive explanations but is limited to simple datasets such as grayscale images. The strength of our approach in creating intuitive explanations that are also quantitatively superior to other methods is demonstrated on three diverse image datasets (skin lesions, faces, and fashion apparel). A user study with 200 participants further exemplifies the benefits of contrastive information, which can be viewed as complementary to other state-of-the-art interpretability methods.