5 papers
ExpertLens: Visualizing Embedding Spaces for Post-Hoc Explainability in MoE Enhanced Retrievers
Effrosyni Sokli, Isaac Roberts, Alexander Schulz +2
Neural models, including dense retrievers, have been widely adopted in Information Retrieval (IR), often delivering state-of-the-art performance. Despite their effectiveness, these…
Explaining Image Similarity with Automatically Extracted Concept Activation Vectors
Isaac Roberts, Petra Bevandic, Alexander Schulz +1
Image similarity underlies many computer vision applications, yet it is often unclear why two images receive a high or low similarity score. Existing explainability methods often r…
Contrastive Concept Importance: Explaining Pairwise Class Decisions Through Automatically Extracted Concept Representations
Roel Visser, Isaac Roberts, Barbara Hammer
Concept-based explanations are a prevalent way to explain the decisions of complex black-box methods through semantically meaningful, human interpretable concepts. To attribute the…
Conceptualizing Uncertainty: A Concept-based Approach to Explaining Uncertainty
Isaac Roberts, Alexander Schulz, Sarah Schroeder +2
Uncertainty in machine learning refers to the degree of confidence or lack thereof in a model's predictions. While uncertainty quantification methods exist, explanations of uncerta…
Targeted Visualization of the Backbone of Encoder LLMs
Isaac Roberts, Alexander Schulz, Luca Hermes +1
Attention based Large Language Models (LLMs) are the state-of-the-art in natural language processing (NLP). The two most common architectures are encoders such as BERT, and decoder…