# Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability

arXiv: https://arxiv.org/abs/2510.00773 · HTML: https://mlsanity.com/paper/2510.00773/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 18 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges](https://mlsanity.com/paper/2103.11251/) (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)
- [Stochastic Concept Bottleneck Models](https://mlsanity.com/paper/2406.19272/) (2024)
- [Leakage and Interpretability in Concept-Based Models](https://mlsanity.com/paper/2504.14094/) (2025)
- [Out-of-Distribution Detection Should Use Conformal Prediction (and Vice-versa?)](https://mlsanity.com/paper/2403.11532/) (2024)

## Abstract (arXiv)

In the context of image classification, Concept Bottleneck Models (CBMs) first embed images into a set of human-understandable concepts, followed by an intrinsically interpretable classifier that predicts labels based on these intermediate representations. While CBMs offer a semantically meaningful and interpretable classification pipeline, they often sacrifice predictive performance compared to end-to-end convolutional neural networks. Moreover, the propagation of uncertainty from concept predictions to final label decisions remains underexplored. In this paper, we propose a novel uncertainty-aware and interpretable classifier for the second stage of CBMs. Our method learns a set of binary class-level concept prototypes and uses the distances between predicted concept vectors and each class prototype as both a classification score and a measure of uncertainty. These prototypes also serve as interpretable classification rules, indicating which concepts should be present in an image to justify a specific class prediction. The proposed framework enhances both interpretability and robustness by enabling conformal prediction for uncertain or outlier inputs based on their deviation from the learned binary class-level concept prototypes.