# UNBOX: Unveiling Black-box visual models with Natural-language

arXiv: https://arxiv.org/abs/2603.08639 · HTML: https://mlsanity.com/paper/2603.08639/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 47 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 30 of 36)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [From Recognition to Cognition: Visual Commonsense Reasoning](https://mlsanity.com/paper/1811.10830/) (2018)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification](https://mlsanity.com/paper/2211.11158/) (2022)
- [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024)
- [No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems](https://mlsanity.com/paper/2011.12945/) (2020)
- [Full-Gradient Representation for Neural Network Visualization](https://mlsanity.com/paper/1905.00780/) (2019)
- [Multimodal Explanations: Justifying Decisions and Pointing to the Evidence](https://mlsanity.com/paper/1802.08129/) (2018)
- [CRAFT: Concept Recursive Activation FacTorization for Explainability](https://mlsanity.com/paper/2211.10154/) (2022)
- [Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations](https://mlsanity.com/paper/2203.01517/) (2022)
- [CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks](https://mlsanity.com/paper/2204.10965/) (2022)
- [Natural Language Descriptions of Deep Visual Features](https://mlsanity.com/paper/2201.11114/) (2022)
- [Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks](https://mlsanity.com/paper/1801.03454/) (2018)
- [Salient ImageNet: How to discover spurious features in Deep Learning?](https://mlsanity.com/paper/2110.04301/) (2021)
- [Grounding Visual Explanations](https://mlsanity.com/paper/1807.09685/) (2018)
- [NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks](https://mlsanity.com/paper/2203.05081/) (2022)
- [Discovering and Mitigating Visual Biases through Keyword Explanation](https://mlsanity.com/paper/2301.11104/) (2023)
- [Concept Activation Regions: A Generalized Framework For Concept-Based Explanations](https://mlsanity.com/paper/2209.11222/) (2022)
- [Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1908.02686/) (2019)
- [Self-explaining AI as an alternative to interpretable AI](https://mlsanity.com/paper/2002.05149/) (2020)
- [HINT: Hierarchical Neuron Concept Explainer](https://mlsanity.com/paper/2203.14196/) (2022)
- [WWW: A Unified Framework for Explaining What, Where and Why of Neural Networks by Interpretation of Neuron Concepts](https://mlsanity.com/paper/2402.18956/) (2024)

## Abstract (arXiv)

Ensuring trustworthiness in open-world visual recognition requires models that are interpretable, fair, and robust to distribution shifts. Yet modern vision systems are increasingly deployed as proprietary black-box APIs, exposing only output probabilities and hiding architecture, parameters, gradients, and training data. This opacity prevents meaningful auditing, bias detection, and failure analysis. Existing explanation methods assume white- or gray-box access or knowledge of the training distribution, making them unusable in these real-world settings. We introduce UNBOX, a framework for class-wise model dissection under fully data-free, gradient-free, and backpropagation-free constraints. UNBOX leverages Large Language Models and text-to-image diffusion models to recast activation maximization as a purely semantic search driven by output probabilities. The method produces human-interpretable text descriptors that maximally activate each class, revealing the concepts a model has implicitly learned, the training distribution it reflects, and potential sources of bias. We evaluate UNBOX on ImageNet-1K, Waterbirds, and CelebA through semantic fidelity tests, visual-feature correlation analyses and slice-discovery auditing. Despite operating under the strictest black-box constraints, UNBOX performs competitively with state-of-the-art white-box interpretability methods. This demonstrates that meaningful insight into a model's internal reasoning can be recovered without any internal access, enabling more trustworthy and accountable visual recognition systems.