# Interpreting and Controlling Vision Foundation Models via Text Explanations

arXiv: https://arxiv.org/abs/2310.10591 · HTML: https://mlsanity.com/paper/2310.10591/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 62 references that are in the map.
- First posted on arXiv 16 Oct 2023.

## Builds on (most cited first, 30 of 51)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [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)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)

## Built on by (most cited first, 11 of 11)

- [Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations](https://mlsanity.com/paper/2410.02762/) (2024)
- [Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery](https://mlsanity.com/paper/2407.14499/) (2024)
- [How Visual Representations Map to Language Feature Space in Multimodal LLMs](https://mlsanity.com/paper/2506.11976/) (2025)
- [To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models](https://mlsanity.com/paper/2510.08510/) (2025)
- [Decomposing and Editing Predictions by Modeling Model Computation](https://mlsanity.com/paper/2404.11534/) (2024)
- [Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval](https://mlsanity.com/paper/2512.03276/) (2025)
- [Knowledge Transfer from Interaction Learning](https://mlsanity.com/paper/2509.18733/) (2025)
- [Towards Understanding Multimodal Fine-Tuning: Spatial Features](https://mlsanity.com/paper/2602.08713/) (2026)
- [TRANSPORTER: Transferring Visual Semantics from VLM Manifolds](https://mlsanity.com/paper/2511.18359/) (2025)
- [Multimodal Model Diffing for Feature Discovery and Control](https://mlsanity.com/paper/2608.09928/) (2026)
- [Using OCR Heads to Verbalize Image Semantics](https://mlsanity.com/paper/2609.18823/) (2026)

## Abstract (arXiv)

Large-scale pre-trained vision foundation models, such as CLIP, have become de facto backbones for various vision tasks. However, due to their black-box nature, understanding the underlying rules behind these models' predictions and controlling model behaviors have remained open challenges. We present a framework for interpreting vision transformer's latent tokens with natural language. Given a latent token, our framework retains its semantic information to the final layer using transformer's local operations and retrieves the closest text for explanation. Our approach enables understanding of model visual reasoning procedure without needing additional model training or data collection. Based on the obtained interpretations, our framework allows for model editing that controls model reasoning behaviors and improves model robustness against biases and spurious correlations.