# Unveiling Ontological Commitment in Multi-Modal Foundation Models

arXiv: https://arxiv.org/abs/2409.17109 · HTML: https://mlsanity.com/paper/2409.17109/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 61 references that are in the map.
- First posted on arXiv 25 Sep 2024.

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [A Survey of Deep Learning Techniques for Autonomous Driving](https://mlsanity.com/paper/1910.07738/) (2019)
- [The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision](https://mlsanity.com/paper/1904.12584/) (2019)
- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks](https://mlsanity.com/paper/1801.03454/) (2018)
- [Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors](https://mlsanity.com/paper/2006.15417/) (2020)
- [PartImageNet: A Large, High-Quality Dataset of Parts](https://mlsanity.com/paper/2112.00933/) (2021)
- [Logic Tensor Networks for Semantic Image Interpretation](https://mlsanity.com/paper/1705.08968/) (2017)
- [A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts](https://mlsanity.com/paper/2105.07190/) (2021)
- [Fine-grained Image Captioning with CLIP Reward](https://mlsanity.com/paper/2205.13115/) (2022)
- [Improving Zero-shot Generalization and Robustness of Multi-modal Models](https://mlsanity.com/paper/2212.01758/) (2022)
- [Concept Embedding Analysis: A Review](https://mlsanity.com/paper/2203.13909/) (2022)
- [ECLAD: Extracting Concepts with Local Aggregated Descriptors](https://mlsanity.com/paper/2206.04531/) (2022)
- [Expressive Explanations of DNNs by Combining Concept Analysis with ILP](https://mlsanity.com/paper/2105.07371/) (2021)
- [Verification of Size Invariance in DNN Activations using Concept Embeddings](https://mlsanity.com/paper/2105.06727/) (2021)
- [CHAIN: Concept-harmonized Hierarchical Inference Interpretation of Deep Convolutional Neural Networks](https://mlsanity.com/paper/2002.01660/) (2020)
- [Enabling Verification of Deep Neural Networks in Perception Tasks Using Fuzzy Logic and Concept Embeddings](https://mlsanity.com/paper/2201.00572/) (2022)
- [Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces](https://mlsanity.com/paper/2311.14435/) (2023)
- [Revealing Similar Semantics Inside CNNs: An Interpretable Concept-based Comparison of Feature Spaces](https://mlsanity.com/paper/2305.07663/) (2023)

## Built on by (most cited first, 1 of 1)

- [Shape Bias and Robustness Evaluation via Cue Decomposition for Image Classification and Segmentation](https://mlsanity.com/paper/2503.12453/) (2025)

## Abstract (arXiv)

Ontological commitment, i.e., used concepts, relations, and assumptions, are a corner stone of qualitative reasoning (QR) models. The state-of-the-art for processing raw inputs, though, are deep neural networks (DNNs), nowadays often based off from multimodal foundation models. These automatically learn rich representations of concepts and respective reasoning. Unfortunately, the learned qualitative knowledge is opaque, preventing easy inspection, validation, or adaptation against available QR models. So far, it is possible to associate pre-defined concepts with latent representations of DNNs, but extractable relations are mostly limited to semantic similarity. As a next step towards QR for validation and verification of DNNs: Concretely, we propose a method that extracts the learned superclass hierarchy from a multimodal DNN for a given set of leaf concepts. Under the hood we (1) obtain leaf concept embeddings using the DNN's textual input modality; (2) apply hierarchical clustering to them, using that DNNs encode semantic similarities via vector distances; and (3) label the such-obtained parent concepts using search in available ontologies from QR. An initial evaluation study shows that meaningful ontological class hierarchies can be extracted from state-of-the-art foundation models. Furthermore, we demonstrate how to validate and verify a DNN's learned representations against given ontologies. Lastly, we discuss potential future applications in the context of QR.