Towards Fine-Grained and Verifiable Concept Bottleneck Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917493931507712 |
|---|---|
| author | Fang, Yingying Xu, Haijie Wu, Shuang Anish, Mariathasan Yang, Guang |
| author_facet | Fang, Yingying Xu, Haijie Wu, Shuang Anish, Mariathasan Yang, Guang |
| contents | Concept Bottleneck Models (CBMs) offer interpretable alternatives to black-box predictors by introducing human-relatable concepts before the final output. However, existing CBMs struggle to verify whether predicted concepts correspond to the correct visual evidence, limiting their reliability. We propose a fine-grained CBM framework that grounds each concept in localized visual evidence, enabling direct inspection of where and how concepts are encoded. This design allows users to interpret predictions and verify that the model learns intended concepts rather than spurious correlations. Experiments on medical imaging benchmarks show that our learned concept space is information-complete and achieves predictive performance comparable to standard CBMs, while substantially improving transparency. Unlike post-hoc attribution methods, our framework validates both the presence and correctness of concept representations, bridging interpretability with verifiability. Our approach enhances the trustworthiness of CBMs and establishes a principled mechanism for human-model interaction at the concept level, paving the way toward more reliable and clinically actionable concept-based learning systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_14210 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Towards Fine-Grained and Verifiable Concept Bottleneck Models Fang, Yingying Xu, Haijie Wu, Shuang Anish, Mariathasan Yang, Guang Machine Learning Artificial Intelligence Concept Bottleneck Models (CBMs) offer interpretable alternatives to black-box predictors by introducing human-relatable concepts before the final output. However, existing CBMs struggle to verify whether predicted concepts correspond to the correct visual evidence, limiting their reliability. We propose a fine-grained CBM framework that grounds each concept in localized visual evidence, enabling direct inspection of where and how concepts are encoded. This design allows users to interpret predictions and verify that the model learns intended concepts rather than spurious correlations. Experiments on medical imaging benchmarks show that our learned concept space is information-complete and achieves predictive performance comparable to standard CBMs, while substantially improving transparency. Unlike post-hoc attribution methods, our framework validates both the presence and correctness of concept representations, bridging interpretability with verifiability. Our approach enhances the trustworthiness of CBMs and establishes a principled mechanism for human-model interaction at the concept level, paving the way toward more reliable and clinically actionable concept-based learning systems. |
| title | Towards Fine-Grained and Verifiable Concept Bottleneck Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2605.14210 |