English
Related papers

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

200 papers

A common goal of mechanistic interpretability is to decompose the activations of neural networks into features: interpretable properties of the input computed by the model. Sparse autoencoders (SAEs) are a popular method for finding these…

Machine Learning · Computer Science 2025-02-10 Patrick Leask , Bart Bussmann , Michael Pearce , Joseph Bloom , Curt Tigges , Noura Al Moubayed , Lee Sharkey , Neel Nanda

Concept Bottleneck Models (CBMs) predict through human-interpretable concepts, but they typically output point concept probabilities that conflate epistemic uncertainty (reducible model underspecification) with aleatoric uncertainty…

Artificial Intelligence · Computer Science 2026-04-28 Tanmoy Mukherjee , Thomas Bailleux , Pierre Marquis , Zied Bouraoui

Despite their impressive performance, generative image models trained on large-scale datasets frequently fail to produce images with seemingly simple concepts -- e.g., human hands or objects appearing in groups of four -- that are…

Graphics · Computer Science 2025-06-25 Matyas Bohacek , Thomas Fel , Maneesh Agrawala , Ekdeep Singh Lubana

The lack of transparency in the decision-making processes of deep learning systems presents a significant challenge in modern artificial intelligence (AI), as it impairs users' ability to rely on and verify these systems. To address this…

Artificial Intelligence · Computer Science 2024-11-18 David Debot , Pietro Barbiero , Francesco Giannini , Gabriele Ciravegna , Michelangelo Diligenti , Giuseppe Marra

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable features. While SAEs provide crucial insights into LLM…

Machine Learning · Computer Science 2025-11-11 Zhen Xu , Zhen Tan , Song Wang , Kaidi Xu , Tianlong Chen

Concept bottleneck model (CBM) is a ubiquitous method that can interpret neural networks using concepts. In CBM, concepts are inserted between the output layer and the last intermediate layer as observable values. This helps in…

Machine Learning · Statistics 2023-03-17 Naoki Hayashi , Yoshihide Sawada

Modern deep neural networks have now reached human-level performance across a variety of tasks. However, unlike humans they lack the ability to explain their decisions by showing where and telling what concepts guided them. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Itay Benou , Tammy Riklin-Raviv

Extreme ocean phenomena are challenging not only to predict but to diagnose, as accurate forecasts alone do not reveal the underlying physical drivers. While recent machine learning approaches achieve strong predictive skill, they remain…

Machine Learning · Computer Science 2026-05-14 Sanah Suri , Kieran Ringel , Maike Sonnewald

Enhancing model interpretability can address spurious correlations by revealing how models draw their predictions. Concept Bottleneck Models (CBMs) can provide a principled way of disclosing and guiding model behaviors through…

Machine Learning · Computer Science 2024-07-15 Jeeyung Kim , Ze Wang , Qiang Qiu

Sparse Autoencoders (SAEs) are a prominent tool in mechanistic interpretability (MI) for decomposing neural network activations into interpretable features. However, the aspiration to identify a canonical set of features is challenged by…

Machine Learning · Computer Science 2025-05-27 Xiangchen Song , Aashiq Muhamed , Yujia Zheng , Lingjing Kong , Zeyu Tang , Mona T. Diab , Virginia Smith , Kun Zhang

Large language models (LLMs) have demonstrated exceptional reasoning capabilities, and co-evolving paradigms have shown promising results in domains such as code and math. However, in scientific reasoning tasks, these models remain fragile…

Artificial Intelligence · Computer Science 2026-02-13 Xiaohan He , Shiyang Feng , Songtao Huang , Lei Bai , Bin Wang , Bo Zhang

Sparse autoencoders (SAEs) have been used widely to decompose and interpret neural network activations, especially those of transformer language models. One key issue with SAEs is their inability to directly model multidimensional features.…

Machine Learning · Computer Science 2026-05-12 Collin Francel

Concept Bottleneck Models (CBMs) map the black-box visual representations extracted by deep neural networks onto a set of interpretable concepts and use the concepts to make predictions, enhancing the transparency of the decision-making…

Machine Learning · Computer Science 2024-04-18 Chenming Shang , Shiji Zhou , Hengyuan Zhang , Xinzhe Ni , Yujiu Yang , Yuwang Wang

Scientific archives now contain hundreds of petabytes of data across genomics, ecology, climate, and molecular biology that could reveal undiscovered patterns if systematically analyzed at scale. Large-scale, weakly-supervised datasets in…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Samuel Stevens , Jacob Beattie , Tanya Berger-Wolf , Yu Su

Interpretability and explainability of neural networks is continuously increasing in importance, especially within safety-critical domains and to provide the social right to explanation. Concept based explanations align well with how humans…

Machine Learning · Computer Science 2023-09-11 Rishabh Jain

Concept Bottleneck Models (CBM) map images to human-interpretable concepts before making class predictions. Recent approaches automate CBM construction by prompting Large Language Models (LLMs) to generate text concepts and employing Vision…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Nithish Muthuchamy Selvaraj , Xiaobao Guo , Adams Wai-Kin Kong , Alex Kot

Concept Bottleneck Models (CBMs) aim to deliver interpretable and interventionable predictions by bridging features and labels with human-understandable concepts. While recent CBMs show promising potential, they suffer from information…

Machine Learning · Computer Science 2024-02-12 Ao Sun , Yuanyuan Yuan , Pingchuan Ma , Shuai Wang

Concept Bottleneck Models (CBMs) are interpretable models that route predictions through a layer of human-interpretable concepts. While widely studied in vision and, more recently, in NLP, CBMs remain largely unexplored in multimodal…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Pierre Moreau , Emeline Pineau Ferrand , Yann Choho , Benjamin Wong , Annabelle Blangero , Milan Bhan

Advancements in foundation models (FMs) have led to a paradigm shift in machine learning. The rich, expressive feature representations from these pre-trained, large-scale FMs are leveraged for multiple downstream tasks, usually via…

Machine Learning · Computer Science 2024-12-19 Jihye Choi , Jayaram Raghuram , Yixuan Li , Somesh Jha

Sparse Autoencoders (SAEs) have been successfully used to probe Large Language Models (LLMs) and extract interpretable concepts from their internal representations. These concepts are linear combinations of neuron activations that…

Computation and Language · Computer Science 2026-02-23 Mathis Le Bail , Jérémie Dentan , Davide Buscaldi , Sonia Vanier
‹ Prev 1 4 5 6 7 8 10 Next ›