Scholar
Roberto Confalonieri
Google Scholar ID: zZPB9jUAAAAJ
University of Padova, Department of Mathematics
Neurosymbolic AI
Explainable AI
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
3,113
H-index
16
i10-index
21
Publications
20
Co-authors
13
list available
Publications
8 items
Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations
2026
Cited
0
Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling
2026
Cited
0
Argumentation-Based Explainability for Legal AI: Comparative and Regulatory Perspectives
2025
Cited
0
(Sometimes) Less is More: Mitigating the Complexity of Rule-based Representation for Interpretable Classification
2025
Cited
0
Iterative In-Context Learning to Enhance LLMs Abstract Reasoning: The Case-Study of Algebraic Tasks
2025
Cited
0
Publish to Perish: Prompt Injection Attacks on LLM-Assisted Peer Review
2025
Cited
0
CUBIC: Concept Embeddings for Unsupervised Bias Identification using VLMs
2025
Cited
0
Extracting PAC Decision Trees from Black Box Binary Classifiers: The Gender Bias Study Case on BERT-based Language Models
AAAI Conference on Artificial Intelligence · 2024
Cited
0
Co-authors
5 total
Tarek R. Besold
Sony AI
Nicolas Troquard
Gran Sasso Science Institute - GSSI
Francisco Herrera
Professor Computer Science and AI, DaSCI Research Institute, Granada University, Spain
Natalia Díaz-Rodríguez, PhD (ORCID: 0000-0003-3362-9326)
Professor, University of Granada, Spain, DaSCI Andalusian Institute on Data Science (RoR:04njjy449)
Carles Sierra
Professor of Artificial Intelligence
