# Are Concept Bottleneck Models Effective as Decision-Support Systems?

arXiv: https://arxiv.org/abs/2608.25581 · HTML: https://mlsanity.com/paper/2608.25581/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 49 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Builds on (most cited first, 5 of 5)

- [Explainable AI improves task performance in human-AI collaboration](https://mlsanity.com/paper/2406.08271/) (2024)
- [The Phish, The Spam, and The Valid: Generating Feature-Rich Emails for Benchmarking LLMs](https://mlsanity.com/paper/2511.21448/) (2025)
- [Towards Reasonable Concept Bottleneck Models](https://mlsanity.com/paper/2506.05014/) (2025)
- [Personalized Interpretability -- Interactive Alignment of Prototypical Parts Networks](https://mlsanity.com/paper/2506.05533/) (2025)
- [Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations](https://mlsanity.com/paper/2605.16405/) (2026)

## Built on by (most cited first, 2 of 2)

- [Should I stay or should I show? Learning to selectively disclose information](https://mlsanity.com/paper/2609.39818/) (2026)
- [When Are Concept Bottleneck Model Explanations Faithful and Compact?](https://mlsanity.com/paper/2610.06285/) (2026)

## Abstract (arXiv)

Concept Bottleneck Models (CBMs) are interpretable-by-design neural networks that detect human-understandable concepts from the input and use them to generate predictions. By allowing users to inspect the concepts underlying a prediction and explore how predictions change under alternative concept configurations, CBMs have emerged as one of the most prominent approaches to supporting human-AI collaboration. However, user studies investigating their actual effectiveness as decision-support systems remain limited. We present two large-scale user studies (N participants = 705, N observations = 6,959) evaluating how concept-based explanations and user interventions on the model's concepts affect the performance of the human-AI team in two distinct binary classification tasks. Our results show that CBMs, and particularly their interactive component, can improve human-AI team accuracy relative to both unaided human performance and performance with non-interpretable AI support. However, these benefits emerge only under certain conditions: classification tasks perceived as difficult, easily identifiable concepts, and active interaction with the model. We also discuss how inaccurate concept detection may undermine users' trust in the model. Overall, this work provides practical guidance for the deployment of CBMs as effective decision-support tools.