9 citations · 17 across the 9 of their papers we have counts for
10 papers
Augmenting Visual Anomaly Detection with Automated Interpretability
Antonio De Santis, Arsenio Leo, Marco Brambilla
Visual anomaly detectors identify deviations from known-normal data, but their anomaly signals may mix evidence of actual anomalies with benign visual variation. We investigate whe…
Prioritization of Risks from Artificial Intelligence: A Delphi Study of 272 International Experts
Alexander K. Saeri, Jess Graham, Michael Noetel +185
Artificial intelligence poses many risks, ranging from familiar present-day harms to unprecedented and potentially catastrophic ones. Effective risk management requires prioritizat…
A Framework for Evaluating Zero-Shot Image Generation in Concept-based Explainability
Giacomo Astolfi, Matteo Bianchi, Riccardo Campi +2
Concept-based Explainable Artificial Intelligence (XAI) interprets deep learning models using human-understandable visual features (e.g., textures or object parts) by linking inter…
Comparing Human and Large Language Model Interpretation of Implicit Information
Antonio De Santis, Tommaso Bonetti, Andrea Tocchetti +1
The interpretation of implicit meanings is an integral aspect of human communication. However, this framework may not transfer to interactions with Large Language Models (LLMs). To…
LLM-Enhanced Semantic Data Integration of Electronic Component Qualifications in the Aerospace Domain
Antonio De Santis, Marco Balduini, Matteo Belcao +3
Large manufacturing companies face challenges in information retrieval due to data silos maintained by different departments, leading to inconsistencies and misalignment across dat…
Learning Concept Bottleneck Models from Mechanistic Explanations
Antonio De Santis, Schrasing Tong, Marco Brambilla +1
Concept Bottleneck Models (CBMs) aim for ante-hoc interpretability by learning a bottleneck layer that predicts interpretable concepts before the decision. State-of-the-art approac…
Enriching Ontologies with Disjointness Axioms using Large Language Models
Elias Crum, Antonio De Santis, Manon Ovide +4
Ontologies often lack explicit disjointness declarations between classes, despite their usefulness for sophisticated reasoning and consistency checking in Knowledge Graphs. In this…
Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification
Antonio De Santis, Riccardo Campi, Matteo Bianchi +1
Convolutional Neural Networks (CNNs) have shown remarkable performance in image classification. However, interpreting their predictions is challenging due to the size and complexit…
Integrating Large Language Models and Knowledge Graphs for Extraction and Validation of Textual Test Data
Antonio De Santis, Marco Balduini, Federico De Santis +4
Aerospace manufacturing companies, such as Thales Alenia Space, design, develop, integrate, verify, and validate products characterized by high complexity and low volume. They care…
Interpretable Network Visualizations: A Human-in-the-Loop Approach for Post-hoc Explainability of CNN-based Image Classification
Matteo Bianchi, Antonio De Santis, Andrea Tocchetti +1
Transparency and explainability in image classification are essential for establishing trust in machine learning models and detecting biases and errors. State-of-the-art explainabi…