From the 1 of 5 linked papers with an AI index.
5 papers
Contrastive Concept Importance: Explaining Pairwise Class Decisions Through Automatically Extracted Concept Representations
Roel Visser, Isaac Roberts, Barbara Hammer
The paper proposes Contrastive Concept Importance (CCI), a method that attributes the logit margin between a target and a foil class to automatically extracted visual concepts, pro…
Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions
Hubert Baniecki, Maximilian Muschalik, Fabian Fumagalli +3
Language-image pre-training (LIP) enables the development of vision-language models capable of zero-shot classification, localization, multimodal retrieval, and semantic understand…
Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory
Fabian Fumagalli, Maximilian Muschalik, Eyke Hüllermeier +2
Feature-based explanations, using perturbations or gradients, are a prevalent tool to understand decisions of black box machine learning models. Yet, differences between these meth…
Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks
Maximilian Muschalik, Fabian Fumagalli, Paolo Frazzetto +5
Albeit the ubiquitous use of Graph Neural Networks (GNNs) in machine learning (ML) prediction tasks involving graph-structured data, their interpretability remains challenging. In…
Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection
Maximilian Spliethöver, Tim Knebler, Fabian Fumagalli +4
Recent advances on instruction fine-tuning have led to the development of various prompting techniques for large language models, such as explicit reasoning steps. However, the suc…