English
Related papers

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

200 papers

The evaluation of large language models (LLMs) relies heavily on standardized benchmarks. These benchmarks provide useful aggregated metrics for a given capability, but those aggregated metrics can obscure (i) particular sub-areas where the…

Computation and Language · Computer Science 2025-12-25 Matyas Bohacek , Nino Scherrer , Nicholas Dufour , Thomas Leung , Christoph Bregler , Stephanie C. Y. Chan

With growing demand for interpretability in deep learning, especially in high stakes domains, Concept Bottleneck Models (CBMs) address this by inserting human understandable concepts into the prediction pipeline, but they are generally…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Jiakai Lin , Jinchang Zhang , Guoyu Lu

Concept bottleneck models (CBMs) are inherently interpretable models that make predictions based on human-understandable visual cues, referred to as concepts. As obtaining dense concept annotations with human labeling is demanding and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-21 Sujin Jeon , Hyundo Lee , Eungseo Kim , Sanghack Lee , Byoung-Tak Zhang , Inwoo Hwang

Concept Bottleneck Models (CBMs) have garnered increasing attention due to their ability to provide concept-based explanations for black-box deep learning models while achieving high final prediction accuracy using human-like concepts.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Lijie Hu , Tianhao Huang , Huanyi Xie , Xilin Gong , Chenyang Ren , Zhengyu Hu , Lu Yu , Ping Ma , Di Wang

Concept Bottleneck Models (CBMs) have emerged as a promising interpretable method whose final prediction is based on intermediate, human-understandable concepts rather than the raw input. Through time-consuming manual interventions, a user…

Machine Learning · Computer Science 2024-10-18 Moritz Vandenhirtz , Sonia Laguna , Ričards Marcinkevičs , Julia E. Vogt

Concept Bottleneck Models (CBMs) are regarded as inherently interpretable because they first predict a set of human-defined concepts which are used to predict a task label. For inherent interpretability to be fully realised, and ensure…

Machine Learning · Computer Science 2024-07-31 Jack Furby , Daniel Cunnington , Dave Braines , Alun Preece

We present Universal Sparse Autoencoders (USAEs), a framework for uncovering and aligning interpretable concepts spanning multiple pretrained deep neural networks. Unlike existing concept-based interpretability methods, which focus on a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Harrish Thasarathan , Julian Forsyth , Thomas Fel , Matthew Kowal , Konstantinos G. Derpanis

The concept bottleneck model (CBM) is an interpretable-by-design framework that makes decisions by first predicting a set of interpretable concepts, and then predicting the class label based on the given concepts. Existing CBMs are trained…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Andong Tan , Fengtao Zhou , Hao Chen

Large Language Models (LLMs) encode factual knowledge within hidden parametric spaces that are difficult to inspect or control. While Sparse Autoencoders (SAEs) can decompose hidden activations into more fine-grained, interpretable…

Machine Learning · Computer Science 2026-01-14 Minglai Yang , Xinyu Guo , Zhengliang Shi , Jinhe Bi , Steven Bethard , Mihai Surdeanu , Liangming Pan

Analyzing large-scale text corpora is a core challenge in machine learning, crucial for tasks like identifying undesirable model behaviors or biases in training data. Current methods often rely on costly LLM-based techniques (e.g.…

Artificial Intelligence · Computer Science 2025-12-12 Nick Jiang , Xiaoqing Sun , Lisa Dunlap , Lewis Smith , Neel Nanda

Concept-bottleneck models (CBMs) are neural classifiers that compute predictions from high-level concepts extracted from the input. CBMs ensure stakeholders can understand the concepts -- and the predictions they entail -- by learning these…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Nicola Debole , Andrea Passerini , Stefano Teso , Andrea Pugnana , Emanuele Marconato

In the context of image classification, Concept Bottleneck Models (CBMs) first embed images into a set of human-understandable concepts, followed by an intrinsically interpretable classifier that predicts labels based on these intermediate…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Haifei Zhang , Patrick Barry , Eduardo Brandao

Sparse autoencoders (SAEs) have become a central tool for interpreting language models. However, two key SAE analyses that remain difficult to scale are (1) matching semantically similar features across multi-layers and (2) compressing…

Machine Learning · Computer Science 2026-05-28 Tue M. Cao , Nguyen Do , My T. Thai

Concept bottleneck models (CBMs) have emerged as critical tools in domains where interpretability is paramount. These models rely on predefined textual descriptions, referred to as concepts, to inform their decision-making process and offer…

Computer Vision and Pattern Recognition · Computer Science 2024-06-14 Maor Dikter , Tsachi Blau , Chaim Baskin

Despite their success, Large-Language Models (LLMs) still face criticism due to their lack of interpretability. Traditional post-hoc interpretation methods, based on attention and gradient-based analysis, offer limited insights as they only…

Computation and Language · Computer Science 2025-07-17 Francesco De Santis , Philippe Bich , Gabriele Ciravegna , Pietro Barbiero , Danilo Giordano , Tania Cerquitelli

Concept Bottleneck Models (CBNMs) are deep learning models that provide interpretability by enforcing a bottleneck layer where predictions are based exclusively on human-understandable concepts. However, this constraint also restricts…

Machine Learning · Computer Science 2025-10-17 David Debot , Giuseppe Marra

Concept Bottleneck Models (CBMs) are neural networks designed to conjoin high performance with ante-hoc interpretability. CBMs work by first mapping inputs (e.g., images) to high-level concepts (e.g., visible objects and their properties)…

Machine Learning · Computer Science 2026-05-12 Nicola Debole , Pietro Barbiero , Francesco Giannini , Andrea Passerini , Stefano Teso , Emanuele Marconato

Concept Bottleneck Models (CBMs) provide explicit interpretations for deep neural networks through concepts and allow intervention with concepts to adjust final predictions. Existing CBMs assume concepts are conditionally independent given…

Machine Learning · Computer Science 2026-05-04 Haotian Xu , Tsui-Wei Weng , Lam M. Nguyen , Tengfei Ma

Concept Bottleneck Models (CBMs) aim to improve interpretability in Deep Learning by structuring predictions through human-understandable concepts, but they provide no way to verify whether learned concepts align with the human's intended…

Machine Learning · Computer Science 2026-05-22 Stefano Colamonaco , David Debot , Pietro Barbiero , Giuseppe Marra

Sparse autoencoders (SAEs) trained on large language model activations output thousands of features that enable mapping to human-interpretable concepts. The current practice for analyzing these features primarily relies on inspecting…

Computation and Language · Computer Science 2026-03-26 Wilson E. Marcílio-Jr , Danilo M. Eler