# LAVA: Explainability for Unsupervised Latent Embeddings

arXiv: https://arxiv.org/abs/2509.21149 · HTML: https://mlsanity.com/paper/2509.21149/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 62 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 14 of 14)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Interpretable machine learning: definitions, methods, and applications](https://mlsanity.com/paper/1901.04592/) (2019)
- [Towards a Definition of Disentangled Representations](https://mlsanity.com/paper/1812.02230/) (2018)
- [Causality for Machine Learning](https://mlsanity.com/paper/1911.10500/) (2019)
- [Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization](https://mlsanity.com/paper/2012.04456/) (2020)
- [Manifold learning: what, how, and why](https://mlsanity.com/paper/2311.03757/) (2023)
- [Concept Activation Regions: A Generalized Framework For Concept-Based Explanations](https://mlsanity.com/paper/2209.11222/) (2022)
- [A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation](https://mlsanity.com/paper/2010.14766/) (2020)
- [Label-Free Explainability for Unsupervised Models](https://mlsanity.com/paper/2203.01928/) (2022)

## Abstract (arXiv)

Unsupervised black-box models are drivers of scientific discovery, yet are difficult to interpret, as their output is often a multidimensional embedding rather than a well-defined target. While explainability for supervised learning uncovers how input features contribute to predictions, its unsupervised counterpart should relate input features to the structure of the learned embeddings. However, adaptations of supervised model explainability for unsupervised learning provide either single-sample or dataset-summary explanations, remaining too fine-grained or reductive to be meaningful, and cannot explain embeddings without mapping functions. To bridge this gap, we propose LAVA, a post-hoc model-agnostic method to explain local embedding organization through feature covariation in the original input data. LAVA explanations comprise modules, capturing local subpatterns of input feature correlation that reoccur globally across the embeddings. LAVA delivers stable explanations at a desired level of granularity, revealing domain-relevant patterns such as visual parts of images or disease signals in cellular processes, otherwise missed by existing methods.