# Clarity: The Flexibility-Interpretability Trade-Off in Sparsity-aware Concept Bottleneck Models

arXiv: https://arxiv.org/abs/2601.21944 · HTML: https://mlsanity.com/paper/2601.21944/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification](https://mlsanity.com/paper/2211.11158/) (2022)
- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [Label-Free Concept Bottleneck Models](https://mlsanity.com/paper/2304.06129/) (2023)
- [Do Concept Bottleneck Models Learn as Intended?](https://mlsanity.com/paper/2105.04289/) (2021)
- [Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability](https://mlsanity.com/paper/2207.09615/) (2022)
- [Zero Shot Recognition with Unreliable Attributes](https://mlsanity.com/paper/1409.4327/) (2014)
- [Coarse-to-Fine Concept Bottleneck Models](https://mlsanity.com/paper/2310.02116/) (2023)
- [Towards Robust Metrics for Concept Representation Evaluation](https://mlsanity.com/paper/2301.10367/) (2023)
- [Sparse Linear Concept Discovery Models](https://mlsanity.com/paper/2308.10782/) (2023)
- [On the Concept Trustworthiness in Concept Bottleneck Models](https://mlsanity.com/paper/2403.14349/) (2024)
- [Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation](https://mlsanity.com/paper/2504.14988/) (2025)
- [If Concept Bottlenecks are the Question, are Foundation Models the Answer?](https://mlsanity.com/paper/2504.19774/) (2025)
- [Contextual Semantic Interpretability](https://mlsanity.com/paper/2009.08720/) (2020)
- [Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning](https://mlsanity.com/paper/2404.03323/) (2024)

## Abstract (arXiv)

The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability. Despite strong performance, these models are often treated as black boxes, with limited systematic investigation of their decision-making processes. While many interpretability methods exist, objective evaluation of learned representations remains limited, particularly for approaches that rely on sparsity to "induce" interpretability. In this work, we investigate how modeling choices in Concept Bottleneck Models (CBMs) affect the semantic alignment of concept representations. We introduce Clarity, a post-hoc diagnostic measure that captures the interplay between downstream performance and the sparsity and precision of concept activations. Using an interpretability assessment framework grounded in datasets with ground-truth concept annotations, we evaluate both VLM- and attribute predictor-based CBMs across three amortized sparsity-inducing strategies (ℓ1, ℓ0, and Bernoulli-based), alongside several widely used sparsity-aware CBM methods from the literature. Our experiments reveal a critical flexibility-interpretability trade-off: a model's capacity to optimize task performance by deviating from semantic alignment. We demonstrate that under this trade-off, different methods exhibit markedly different behaviors even at comparable performance levels. Finally, we validate our framework through a principled human study, which confirms that Clarity aligns significantly more closely with human trust than standard evaluation metrics.