# AnyCBMs: How to Turn Any Black Box into a Concept Bottleneck Model

arXiv: https://arxiv.org/abs/2405.16508 · HTML: https://mlsanity.com/paper/2405.16508/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 26 May 2024.

## Builds on (most cited first, 7 of 7)

- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [On Completeness-aware Concept-Based Explanations in Deep Neural Networks](https://mlsanity.com/paper/1910.07969/) (2019)
- [Promises and Pitfalls of Black-Box Concept Learning Models](https://mlsanity.com/paper/2106.13314/) (2021)
- [Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off](https://mlsanity.com/paper/2209.09056/) (2022)
- [Entropy-based Logic Explanations of Neural Networks](https://mlsanity.com/paper/2106.06804/) (2021)
- [GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks](https://mlsanity.com/paper/2107.11889/) (2021)

## Built on by (most cited first, 5 of 5)

- [If Concept Bottlenecks are the Question, are Foundation Models the Answer?](https://mlsanity.com/paper/2504.19774/) (2025)
- [Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens](https://mlsanity.com/paper/2502.11245/) (2025)
- [Concept Layers: Enhancing Interpretability and Intervenability via LLM Conceptualization](https://mlsanity.com/paper/2502.13632/) (2025)
- [Logic Explanation of AI Classifiers by Categorical Explaining Functors](https://mlsanity.com/paper/2503.16203/) (2025)
- [SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better Interpretability](https://mlsanity.com/paper/2601.12804/) (2026)

## Abstract (arXiv)

Interpretable deep learning aims at developing neural architectures whose decision-making processes could be understood by their users. Among these techniqes, Concept Bottleneck Models enhance the interpretability of neural networks by integrating a layer of human-understandable concepts. These models, however, necessitate training a new model from the beginning, consuming significant resources and failing to utilize already trained large models. To address this issue, we introduce "AnyCBM", a method that transforms any existing trained model into a Concept Bottleneck Model with minimal impact on computational resources. We provide both theoretical and experimental insights showing the effectiveness of AnyCBMs in terms of classification performances and effectivenss of concept-based interventions on downstream tasks.