English
Related papers

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

200 papers

Interpretability is critical in high-stakes domains such as medical imaging, where understanding model decisions is essential for clinical adoption. In this work, we introduce Sparse Autoencoder (SAE)-based interpretability to breast…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Krishna Kanth Nakka

Sparse autoencoders (SAEs) are a popular technique for interpreting language model activations, and there is extensive recent work on improving SAE effectiveness. However, most prior work evaluates progress using unsupervised proxy metrics…

Ensuring fairness in image classification prevents models from perpetuating and amplifying bias. Concept bottleneck models (CBMs) map images to high-level, human-interpretable concepts before making predictions via a sparse, one-layer…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Schrasing Tong , Antoine Salaun , Vincent Yuan , Annabel Adeyeri , Lalana Kagal

Concept Bottleneck Models (CBMs) have emerged as a prominent paradigm for interpretable deep learning, learning by grounding predictions in human-understandable concepts. However, their practical deployment is hindered by the high cost of…

Machine Learning · Computer Science 2026-05-29 Ziye Chen , Hongbin Lin , Jie Li , Lijie Hu

Sparse dictionary learning (and, in particular, sparse autoencoders) attempts to learn a set of human-understandable concepts that can explain variation on an abstract space. A basic limitation of this approach is that it neither exploits…

Computation and Language · Computer Science 2025-06-03 Mark Muchane , Sean Richardson , Kiho Park , Victor Veitch

Sparse autoencoders (SAEs) are increasingly used for safety-relevant applications including alignment detection and model steering. These use cases require SAE latents to be as atomic as possible. Each latent should represent a single…

Machine Learning · Computer Science 2026-04-07 Matthew Levinson

Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by finding sparse, linear reconstructions of LM activations. We…

Machine Learning · Computer Science 2024-05-01 Senthooran Rajamanoharan , Arthur Conmy , Lewis Smith , Tom Lieberum , Vikrant Varma , János Kramár , Rohin Shah , Neel Nanda

Concept Bottleneck Models (CBMs) are machine learning models that improve interpretability by grounding their predictions on human-understandable concepts, allowing for targeted interventions in their decision-making process. However, when…

Sparse autoencoders (SAEs) have recently emerged as pivotal tools for introspection into large language models. SAEs can uncover high-quality, interpretable features at different levels of granularity and enable targeted steering of the…

Information Retrieval · Computer Science 2026-01-19 Martin Spišák , Ladislav Peška , Petr Škoda , Vojtěch Vančura , Rodrigo Alves

Concept-based learning enhances prediction accuracy and interpretability by leveraging high-level, human-understandable concepts. However, existing CBL frameworks do not address survival analysis tasks, which involve predicting event times…

Machine Learning · Computer Science 2025-02-11 Stanislav R. Kirpichenko , Lev V. Utkin , Andrei V. Konstantinov , Natalya M. Verbova

Concept bottleneck models (CBMs), which predict human-interpretable concepts (e.g., nucleus shapes in cell images) before predicting the final output (e.g., cell type), provide insights into the decision-making processes of the model.…

Computer Vision and Pattern Recognition · Computer Science 2024-07-10 Winnie Pang , Xueyi Ke , Satoshi Tsutsui , Bihan Wen

Vision foundation models (FMs) achieve state-of-the-art performance in medical imaging. However, they encode information in abstract latent representations that clinicians cannot interrogate or verify. The goal of this study is to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Philipp Wesp , Robbie Holland , Vasiliki Sideri-Lampretsa , Sergios Gatidis

Understanding and mitigating the potential risks associated with foundation models (FMs) hinges on developing effective interpretability methods. Sparse Autoencoders (SAEs) have emerged as a promising tool for disentangling FM…

Machine Learning · Computer Science 2024-11-04 Aashiq Muhamed , Mona Diab , Virginia Smith

Concept Bottleneck Models (CBMs) introduce interpretability to black-box deep learning models by predicting labels through human-understandable concepts. However, unlike humans, who identify objects at different levels of abstraction using…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Haodong Xie , Yujun Cai , Rahul Singh Maharjan , Yiwei Wang , Federico Tavella , Angelo Cangelosi

Concept bottleneck models (CBM) are a popular way of creating more interpretable neural networks by having hidden layer neurons correspond to human-understandable concepts. However, existing CBMs and their variants have two crucial…

Machine Learning · Computer Science 2023-06-06 Tuomas Oikarinen , Subhro Das , Lam M. Nguyen , Tsui-Wei Weng

Sparse Autoencoders (SAEs) provide potentials for uncovering structured, human-interpretable representations in Large Language Models (LLMs), making them a crucial tool for transparent and controllable AI systems. We systematically analyze…

Machine Learning · Computer Science 2026-02-03 Jack Gallifant , Shan Chen , Kuleen Sasse , Hugo Aerts , Thomas Hartvigsen , Danielle S. Bitterman

While deep learning models often lack interpretability, concept bottleneck models (CBMs) provide inherent explanations via their concept representations. Moreover, they allow users to perform interventional interactions on these concepts by…

Machine Learning · Computer Science 2024-06-05 David Steinmann , Wolfgang Stammer , Felix Friedrich , Kristian Kersting

Techniques for concept extraction, such as sparse autoencoders and transcoders, aim to extract high-level symbolic concepts from low-level nonsymbolic representations. When these extracted concepts are used for downstream tasks such as…

Machine Learning · Computer Science 2026-04-29 Chandler Squires , Pradeep Ravikumar

The linear representation hypothesis states that neural network activations encode high-level concepts as linear mixtures. However, under superposition, this encoding is a projection from a higher-dimensional concept space into a…

Machine Learning · Computer Science 2026-03-31 Vitória Barin Pacela , Shruti Joshi , Isabela Camacho , Simon Lacoste-Julien , David Klindt

Concept Bottleneck Models (CBMs) ground image classification on human-understandable concepts to allow for interpretable model decisions. Crucially, the CBM design inherently allows for human interventions, in which expert users are given…

Machine Learning · Computer Science 2024-08-07 Nishad Singhi , Jae Myung Kim , Karsten Roth , Zeynep Akata