English
Related papers

Related papers: A Geometric Unification of Concept Learning with C…

200 papers

Concept Bottleneck Models (CBMs) provide a basis for semantic abstractions within a neural network architecture. Such models have primarily been seen through the lens of interpretability so far, wherein they offer transparency by inferring…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Deepika SN Vemuri , Gautham Bellamkonda , Aditya Pola , Vineeth N Balasubramanian

The Linear Representation Hypothesis asserts that the embeddings learned by neural networks can be understood as linear combinations of features corresponding to high-level concepts. Based on this ansatz, sparse autoencoders (SAEs) have…

Machine Learning · Computer Science 2026-01-29 Chiraag Kaushik , Davis Barch , Andrea Fanelli

Intermediate layers of large language models (LLMs) best predict human brain responses to language, one of the most robust findings in computational neurolinguistics, yet why remains mechanistically unexplained. We address this gap by…

Computation and Language · Computer Science 2026-05-25 Dongxin Guo , Jikun Wu , Siu Ming Yiu

Sparse Autoencoders (SAEs) have emerged as a predominant tool in mechanistic interpretability, aiming to identify interpretable monosemantic features. However, how does sparse encoding organize the representations of activation vector from…

Machine Learning · Computer Science 2025-05-29 Wenjie Sun , Bingzhe Wu , Zhile Yang , Chengke Wu

Machine learning is a vital part of many real-world systems, but several concerns remain about the lack of interpretability, explainability and robustness of black-box AI systems. Concept Bottleneck Models (CBM) address some of these…

Machine Learning · Statistics 2025-10-24 Hidde Fokkema , Tim van Erven , Sara Magliacane

Sparse autoencoders (SAEs) have emerged as a powerful technique for extracting human-interpretable features from neural networks activations. Previous works compared different models based on SAE-derived features but those comparisons have…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Clément Cornet , Romaric Besançon , Hervé Le Borgne

The Universality Hypothesis in large language models (LLMs) claims that different models converge towards similar concept representations in their latent spaces. Providing evidence for this hypothesis would enable researchers to exploit…

Machine Learning · Computer Science 2025-05-22 Michael Lan , Philip Torr , Austin Meek , Ashkan Khakzar , David Krueger , Fazl Barez

Sparse autoencoders (SAEs) have recently become central tools for interpretability, leveraging dictionary learning principles to extract sparse, interpretable features from neural representations whose underlying structure is typically…

Machine Learning · Computer Science 2025-11-05 Valérie Costa , Thomas Fel , Ekdeep Singh Lubana , Bahareh Tolooshams , Demba Ba

Standard Sparse Autoencoders (SAEs) excel at discovering a dictionary of a model's learned features, offering a powerful observational lens. However, the ambiguous and ungrounded nature of these features makes them unreliable instruments…

Machine Learning · Computer Science 2025-09-29 Jianrong Ding , Muxi Chen , Chenchen Zhao , Qiang Xu

Sparse Autoencoders (SAEs) have emerged as a powerful framework for machine learning interpretability, enabling the unsupervised decomposition of model representations into a dictionary of abstract, human-interpretable concepts. However, we…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Thomas Fel , Ekdeep Singh Lubana , Jacob S. Prince , Matthew Kowal , Victor Boutin , Isabel Papadimitriou , Binxu Wang , Martin Wattenberg , Demba Ba , Talia Konkle

The Concept Bottleneck Models (CBMs) of Koh et al. [2020] provide a means to ensure that a neural network based classifier bases its predictions solely on human understandable concepts. The concept labels, or rationales as we refer to them,…

Machine Learning · Computer Science 2022-12-20 Joshua Lockhart , Daniele Magazzeni , Manuela Veloso

Concept Bottleneck Models (CBMs) tackle the opacity of neural architectures by constructing and explaining their predictions using a set of high-level concepts. A special property of these models is that they permit concept interventions,…

Concept Bottleneck Models (CBMs) enhance the interpretability of neural networks by basing predictions on human-understandable concepts. However, current CBMs typically rely on concept sets extracted from large language models or extensive…

Computer Vision and Pattern Recognition · Computer Science 2025-07-03 Katharina Prasse , Patrick Knab , Sascha Marton , Christian Bartelt , Margret Keuper

There has been considerable recent interest in interpretable concept-based models such as Concept Bottleneck Models (CBMs), which first predict human-interpretable concepts and then map them to output classes. To reduce reliance on…

Machine Learning · Computer Science 2024-07-08 Simon Schrodi , Julian Schur , Max Argus , Thomas Brox

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…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Xingbo Du , Qiantong Dou , Lei Fan , Rui Zhang

Sparse autoencoders (SAEs) are used to analyze embeddings, but their role and practical value are debated. We propose a new perspective on SAEs by demonstrating that they can be naturally understood as topic models. We propose a continuous…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Leander Girrbach , Zeynep Akata

Concept Bottleneck Models (CBMs) try to make the decision-making process transparent by exploring an intermediate concept space between the input image and the output prediction. Existing CBMs just learn coarse-grained relations between the…

Computer Vision and Pattern Recognition · Computer Science 2025-05-13 Yan Xie , Zequn Zeng , Hao Zhang , Yucheng Ding , Yi Wang , Zhengjue Wang , Bo Chen , Hongwei Liu

Concept Bottleneck Models (CBMs) have been proposed as a compromise between white-box and black-box models, aiming to achieve interpretability without sacrificing accuracy. The standard training procedure for CBMs is to predefine a…

Machine Learning · Computer Science 2025-12-05 Jean Feng , Avni Kothari , Luke Zier , Chandan Singh , Yan Shuo Tan

Concept Bottleneck Models (CBMs) have recently been proposed to address the 'black-box' problem of deep neural networks, by first mapping images to a human-understandable concept space and then linearly combining concepts for…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Sukrut Rao , Sweta Mahajan , Moritz Böhle , Bernt Schiele

Recently impressive performance has been achieved in Concept Bottleneck Models (CBM) by utilizing the image-text alignment learned by a large pre-trained vision-language model (i.e. CLIP). However, there exist two key limitations in concept…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Minghong Zhong , Guoshuai Zou , Kanghao Chen , Dexia Chen , Ruixuan Wang