# Flexible Concept Bottleneck Model

arXiv: https://arxiv.org/abs/2511.06678 · HTML: https://mlsanity.com/paper/2511.06678/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 27 of 27)

- [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)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification](https://mlsanity.com/paper/1602.02068/) (2016)
- [VirTex: Learning Visual Representations from Textual Annotations](https://mlsanity.com/paper/2006.06666/) (2020)
- [Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification](https://mlsanity.com/paper/2211.11158/) (2022)
- [Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions](https://mlsanity.com/paper/1710.04806/) (2017)
- [SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding](https://mlsanity.com/paper/2310.15308/) (2023)
- [Concept Bottleneck Model with Additional Unsupervised Concepts](https://mlsanity.com/paper/2202.01459/) (2022)
- [VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance](https://mlsanity.com/paper/2408.01432/) (2024)
- [Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language](https://mlsanity.com/paper/2306.16410/) (2023)
- [Now You See Me (CME): Concept-based Model Extraction](https://mlsanity.com/paper/2010.13233/) (2020)
- [Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning](https://mlsanity.com/paper/2405.16507/) (2024)
- [Rethinking Influence Functions of Neural Networks in the Over-parameterized Regime](https://mlsanity.com/paper/2112.08297/) (2021)
- [Explain via Any Concept: Concept Bottleneck Model with Open Vocabulary Concepts](https://mlsanity.com/paper/2408.02265/) (2024)
- [State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding](https://mlsanity.com/paper/2309.12482/) (2023)
- [Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation](https://mlsanity.com/paper/2503.12068/) (2025)
- [Way to Specialist: Closing Loop Between Specialized LLM and Evolving Domain Knowledge Graph](https://mlsanity.com/paper/2411.19064/) (2024)

## Built on by (most cited first, 1 of 1)

- [Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations](https://mlsanity.com/paper/2609.38625/) (2026)

## Abstract (arXiv)

Concept bottleneck models (CBMs) improve neural network interpretability by introducing an intermediate layer that maps human-understandable concepts to predictions. Recent work has explored the use of vision-language models (VLMs) to automate concept selection and annotation. However, existing VLM-based CBMs typically require full model retraining when new concepts are involved, which limits their adaptability and flexibility in real-world scenarios, especially considering the rapid evolution of vision-language foundation models. To address these issues, we propose Flexible Concept Bottleneck Model (FCBM), which supports dynamic concept adaptation, including complete replacement of the original concept set. Specifically, we design a hypernetwork that generates prediction weights based on concept embeddings, allowing seamless integration of new concepts without retraining the entire model. In addition, we introduce a modified sparsemax module with a learnable temperature parameter that dynamically selects the most relevant concepts, enabling the model to focus on the most informative features. Extensive experiments on five public benchmarks demonstrate that our method achieves accuracy comparable to state-of-the-art baselines with a similar number of effective concepts. Moreover, the model generalizes well to unseen concepts with just a single epoch of fine-tuning, demonstrating its strong adaptability and flexibility.