相关论文: Probing the Probes: Methods and Metrics for Concep…

How can we understand classification decisions made by deep neural networks? Many existing explainability methods rely solely on correlations and fail to account for confounding, which may result in potentially misleading explanations. To…

Interpreting the inner workings of deep learning models is crucial for establishing trust and ensuring model safety. Concept-based explanations have emerged as a superior approach that is more interpretable than feature attribution…

With the rise of deep neural networks, especially in safety-critical applications, robustness and interpretability are crucial to ensure their trustworthiness. Recent advances in 3D-aware classifiers that map image features to volumetric…

Due to their powerful feature association capabilities, neural network-based computer vision models have the ability to detect and exploit unintended patterns within the data, potentially leading to correct predictions based on incorrect or…

Probing (or diagnostic classification) has become a popular strategy for investigating whether a given set of intermediate features is present in the representations of neural models. Probing studies may have misleading results, but various…

Value alignment is essential for building AI systems that can safely and reliably interact with people. However, what a person values -- and is even capable of valuing -- depends on the concepts that they are currently using to understand…

Weakly supervised object localization aims to find a target object region in a given image with only weak supervision, such as image-level labels. Most existing methods use a class activation map (CAM) to generate a localization map;…

The focus of recent research has shifted from merely improving the metrics based performance of Deep Neural Networks (DNNs) to DNNs which are more interpretable to humans. The field of eXplainable Artificial Intelligence (XAI) has observed…

As the request for deep learning solutions increases, the need for explainability is even more fundamental. In this setting, particular attention has been given to visualization techniques, that try to attribute the right relevance to each…

How interpretable are the features of leading vision models? The question is increasingly pressing as these models move from research benchmarks into high-stakes deployments, yet existing methods cannot answer it reliably. We close this gap…

Calibrated confidence estimates obtained from neural networks are crucial, particularly for safety-critical applications such as autonomous driving or medical image diagnosis. However, although the task of confidence calibration has been…

We propose a new approach to promote safety in classification tasks with established concepts. Our approach -- called a conceptual safeguard -- acts as a verification layer for models that predict a target outcome by first predicting the…

Modern AI models contain much of human knowledge, yet understanding of their internal representation of this knowledge remains elusive. Characterizing the structure and properties of this representation will lead to improvements in model…

Mean field variational inference (VI) is the problem of finding the closest product (factorized) measure, in the sense of relative entropy, to a given high-dimensional probability measure $\rho$. The well known Coordinate Ascent Variational…

Recent advances in deep learning have achieved impressive gains in classification accuracy on a variety of types of data, including images and text. Despite these gains, however, concerns have been raised about the calibration, robustness,…

How can we know whether new mechanistic interpretability methods achieve real improvements? In pursuit of lasting evaluation standards, we propose MIB, a Mechanistic Interpretability Benchmark, with two tracks spanning four tasks and five…

Explainable AI (XAI) is crucial for building transparent and trustworthy machine learning systems, especially in high-stakes domains. Concept Bottleneck Models (CBMs) have emerged as a promising ante-hoc approach that provides…

Vision-language models (VLMs) offer flexible object detection through natural language prompts but suffer from performance variability depending on prompt phrasing. In this paper, we introduce a method for automated prompt refinement using…

Learning vectors that capture the meaning of concepts remains a fundamental challenge. Somewhat surprisingly, perhaps, pre-trained language models have thus far only enabled modest improvements to the quality of such concept embeddings.…

Explainability is a longstanding challenge in deep learning, especially in high-stakes domains like healthcare. Common explainability methods highlight image regions that drive an AI model's decision. Humans, however, heavily rely on…