English
Related papers

Related papers: Debugging Concept Bottleneck Models through Remova…

200 papers

While RFML is expected to be a key enabler of future wireless standards, a significant challenge to the widespread adoption of RFML techniques is the lack of explainability in deep learning models. This work investigates the use of CB…

Signal Processing · Electrical Eng. & Systems 2021-01-06 Lauren J. Wong , Sean McPherson

Concept-Based Models (CBMs) are a class of deep learning models that provide interpretability by explaining predictions through high-level concepts. These models first predict concepts and then use them to perform a downstream task.…

Machine Learning · Computer Science 2025-06-27 David Debot , Pietro Barbiero , Gabriele Dominici , Giuseppe Marra

Continuous prompts have become widely adopted for augmenting performance across a wide range of natural language tasks. However, the underlying mechanism of this enhancement remains obscure. Previous studies rely on individual words for…

Computation and Language · Computer Science 2024-12-06 Qian Chen , Dongyang Li , Xiaofeng He

Concept bottleneck models are interpretable predictive models that are often used in domains where model trust is a key priority, such as healthcare. They identify a small number of human-interpretable concepts in the data, which they then…

Machine Learning · Computer Science 2024-12-25 Katrina Brown , Marton Havasi , Finale Doshi-Velez

There is growing interest in concept-based models (CBMs) that combine high-performance and interpretability by acquiring and reasoning with a vocabulary of high-level concepts. A key requirement is that the concepts be interpretable.…

Machine Learning · Computer Science 2022-10-19 Emanuele Marconato , Andrea Passerini , Stefano Teso

We introduce the Consensus-Bottleneck Asset Pricing Model (CB-APM), which embeds aggregate analyst consensus as a structural bottleneck, treating professional beliefs as a sufficient statistic for the market's high-dimensional information…

Pricing of Securities · Quantitative Finance 2026-04-27 Changeun Kim , Younwoo Jeong , Bong-Gyu Jang

Automated essay scoring (AES) has advanced significantly with neural language models, yet most systems remain opaque, offering little visibility into how grades are produced. In educational settings, instructors must be able to understand,…

Computation and Language · Computer Science 2026-04-22 Kumar Satvik Chaudhary , Chengshuai Zhao , Fan Zhang , Garima Agrawal , Yuli Deng , Huan Liu

Effective adaptation to distribution shifts in training data is pivotal for sustaining robustness in neural networks, especially when removing specific biases or outdated information, a process known as machine unlearning. Traditional…

Machine Learning · Computer Science 2024-05-24 Ling Han , Hao Huang , Dustin Scheinost , Mary-Anne Hartley , María Rodríguez Martínez

We introduce Concept Bottleneck Protein Language Models (CB-pLM), a generative masked language model with a layer where each neuron corresponds to an interpretable concept. Our architecture offers three key benefits: i) Control: We can…

Mechanistic interpretability focuses on reverse engineering the internal mechanisms learned by neural networks. We extend our focus and propose to mechanistically forward engineer using our framework based on Concept Bottleneck Models. In…

Machine Learning · Computer Science 2025-12-01 Angela van Sprang , Erman Acar , Willem Zuidema

In human-AI collaboration, a central challenge is deciding whether the AI should handle a task, be deferred to a human expert, or be addressed through collaborative effort. Existing Learning to Defer approaches typically make binary choices…

Artificial Intelligence · Computer Science 2025-05-27 Chengbo He , Bochao Zou , Junliang Xing , Jiansheng Chen , Yuanchun Shi , Huimin Ma

Automated ICD-10 coding from clinical discharge summaries requires models that are both accurate on long-tailed multi-label classification tasks and interpretable to clinicians. Concept Bottleneck Models (CBMs) offer a principled framework…

Machine Learning · Computer Science 2026-05-12 Mohammed Sameer Syed , Xuan Lu

The task of "unlearning" certain concepts in large language models (LLMs) has attracted immense attention recently, due to its importance in mitigating undesirable model behaviours, such as the generation of harmful, private, or incorrect…

Computation and Language · Computer Science 2025-09-03 Yihuai Hong , Lei Yu , Haiqin Yang , Shauli Ravfogel , Mor Geva

Despite their remarkable performance on a wide range of visual tasks, machine learning technologies often succumb to data distribution shifts. Consequently, a range of recent work explores techniques for detecting these shifts.…

Machine Learning · Computer Science 2021-05-04 Maleakhi A. Wijaya , Dmitry Kazhdan , Botty Dimanov , Mateja Jamnik

To increase the trustworthiness of deep neural networks, it is critical to improve the understanding of how they make decisions. This paper introduces a novel unsupervised concept-based model for image classification, named Learnable…

Machine Learning · Computer Science 2025-06-04 Francesco De Santis , Philippe Bich , Gabriele Ciravegna , Pietro Barbiero , Danilo Giordano , Tania Cerquitelli

Deep learning models have achieved remarkable success in different areas of machine learning over the past decade; however, the size and complexity of these models make them difficult to understand. In an effort to make them more…

Computer Vision and Pattern Recognition · Computer Science 2022-06-20 Vikram V. Ramaswamy , Sunnie S. Y. Kim , Nicole Meister , Ruth Fong , Olga Russakovsky

Behavior Cloning (BC) is a widely adopted visual imitation learning method in robot manipulation. Current BC approaches often enhance generalization by leveraging large datasets and incorporating additional visual and textual modalities to…

Robotics · Computer Science 2025-05-14 Shuanghao Bai , Wanqi Zhou , Pengxiang Ding , Wei Zhao , Donglin Wang , Badong Chen

We are concerned with the challenge of reliably classifying and assessing intracranial aneurysms using deep learning without compromising clinical transparency. While traditional black-box models achieve high predictive accuracy, their lack…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Toqa Khaled , Ahmad Al-Kabbany

Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…

Machine Learning · Computer Science 2020-12-08 Isaac Lage , Finale Doshi-Velez

Concept bottleneck models perform classification by first predicting which of a list of human provided concepts are true about a datapoint. Then a downstream model uses these predicted concept labels to predict the target label. The…

Machine Learning · Computer Science 2022-11-08 Joshua Lockhart , Nicolas Marchesotti , Daniele Magazzeni , Manuela Veloso