# Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?

arXiv: https://arxiv.org/abs/2401.13544 · HTML: https://mlsanity.com/paper/2401.13544/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 58 references that are in the map.
- First posted on arXiv 24 Jan 2024.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously](https://mlsanity.com/paper/1801.01489/) (2018)
- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [Label-Free Concept Bottleneck Models](https://mlsanity.com/paper/2304.06129/) (2023)
- [On Completeness-aware Concept-Based Explanations in Deep Neural Networks](https://mlsanity.com/paper/1910.07969/) (2019)
- [Concept Whitening for Interpretable Image Recognition](https://mlsanity.com/paper/2002.01650/) (2020)
- [Promises and Pitfalls of Black-Box Concept Learning Models](https://mlsanity.com/paper/2106.13314/) (2021)
- [Do Concept Bottleneck Models Learn as Intended?](https://mlsanity.com/paper/2105.04289/) (2021)
- [Probabilistic Concept Bottleneck Models](https://mlsanity.com/paper/2306.01574/) (2023)
- [Concept Bottleneck Model with Additional Unsupervised Concepts](https://mlsanity.com/paper/2202.01459/) (2022)
- [Interactive Concept Bottleneck Models](https://mlsanity.com/paper/2212.07430/) (2022)
- [GlanceNets: Interpretabile, Leak-proof Concept-based Models](https://mlsanity.com/paper/2205.15612/) (2022)
- [A Closer Look at the Intervention Procedure of Concept Bottleneck Models](https://mlsanity.com/paper/2302.14260/) (2023)

## Built on by (most cited first, 28 of 28)

- [Stochastic Concept Bottleneck Models](https://mlsanity.com/paper/2406.19272/) (2024)
- [Mechanistic Interpretability of Emotion Inference in Large Language Models](https://mlsanity.com/paper/2502.05489/) (2025)
- [Concept Bottleneck Models Without Predefined Concepts](https://mlsanity.com/paper/2407.03921/) (2024)
- [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)
- [Interpretable Generative Models through Post-hoc Concept Bottlenecks](https://mlsanity.com/paper/2503.19377/) (2025)
- [Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts](https://mlsanity.com/paper/2504.17921/) (2025)
- [Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization](https://mlsanity.com/paper/2504.18026/) (2025)
- [TEARS: Textual Representations for Scrutable Recommendations](https://mlsanity.com/paper/2410.19302/) (2024)
- [Partially Shared Concept Bottleneck Models](https://mlsanity.com/paper/2511.22170/) (2025)
- [LogicCBMs: Logic-Enhanced Concept-Based Learning](https://mlsanity.com/paper/2512.07383/) (2025)
- [Foundations of Interpretable Models](https://mlsanity.com/paper/2508.00545/) (2025)
- [Actionable Interpretability Must Be Defined in Terms of Symmetries](https://mlsanity.com/paper/2601.12913/) (2026)
- [Incorporating Expert Rules into Neural Networks in the Framework of Concept-Based Learning](https://mlsanity.com/paper/2402.14726/) (2024)
- [Interpretable Reward Modeling with Active Concept Bottlenecks](https://mlsanity.com/paper/2507.04695/) (2025)
- [From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection](https://mlsanity.com/paper/2505.06003/) (2025)
- [Process-Guided Concept Bottleneck Model](https://mlsanity.com/paper/2601.10562/) (2026)
- [FI-CBL: A Probabilistic Method for Concept-Based Learning with Expert Rules](https://mlsanity.com/paper/2406.19897/) (2024)
- [Are They the Same Picture? Adapting Concept Bottleneck Models for Human-AI Collaboration in Image Retrieval](https://mlsanity.com/paper/2407.08908/) (2024)
- [Exploiting Interpretable Capabilities with Concept-Enhanced Diffusion and Prototype Networks](https://mlsanity.com/paper/2410.18705/) (2024)
- [Concept-driven Off Policy Evaluation](https://mlsanity.com/paper/2411.19395/) (2024)
- [Intervening in Black Box: Concept Bottleneck Model for Enhancing Human Neural Network Mutual Understanding](https://mlsanity.com/paper/2506.22803/) (2025)
- [Improving ARDS Diagnosis Through Context-Aware Concept Bottleneck Models](https://mlsanity.com/paper/2508.09719/) (2025)
- [Post-hoc Stochastic Concept Bottleneck Models](https://mlsanity.com/paper/2510.08219/) (2025)
- [TRANSPORTER: Transferring Visual Semantics from VLM Manifolds](https://mlsanity.com/paper/2511.18359/) (2025)
- [Federated Concept-Based Models: Interpretable models with distributed supervision](https://mlsanity.com/paper/2602.04093/) (2026)
- [In Defense of Information Leakage in Concept-based Models](https://mlsanity.com/paper/2606.10669/) (2026)
- [When Do Frozen VLMs Respond to Image-Free Object-Token Edits? An Answer-Key-Free Protocol and What It Reveals](https://mlsanity.com/paper/2609.03429/) (2026)

## Abstract (arXiv)

Recently, interpretable machine learning has re-explored concept bottleneck models (CBM). An advantage of this model class is the user's ability to intervene on predicted concept values, affecting the downstream output. In this work, we introduce a method to perform such concept-based interventions on pretrained neural networks, which are not interpretable by design, only given a small validation set with concept labels. Furthermore, we formalise the notion of intervenability as a measure of the effectiveness of concept-based interventions and leverage this definition to fine-tune black boxes. Empirically, we explore the intervenability of black-box classifiers on synthetic tabular and natural image benchmarks. We focus on backbone architectures of varying complexity, from simple, fully connected neural nets to Stable Diffusion. We demonstrate that the proposed fine-tuning improves intervention effectiveness and often yields better-calibrated predictions. To showcase the practical utility of our techniques, we apply them to deep chest X-ray classifiers and show that fine-tuned black boxes are more intervenable than CBMs. Lastly, we establish that our methods are still effective under vision-language-model-based concept annotations, alleviating the need for a human-annotated validation set.