From the 1 of 6 linked papers with an AI index.
6 papers
EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents
Luigi Sigillo, Matteo Silvestri, Francesco Tabaro +9
The paper presents EMBL AI Librarian, a system that lets AI agents query life‑science literature in natural language by using an LLM to generate sub‑queries, retrieve papers from E…
When Large Language Models Know the Table: A Framework for Assessing Data Contamination in Tabular Datasets
Matteo Silvestri, Fabiano Veglianti, Flavio Giorgi +2
Large language models (LLMs) are increasingly exposed to data contamination, i.e., performance gains driven by prior exposure of test datasets rather than generalization. However,…
PONTE: Personalized Orchestration for Natural Language Trustworthy Explanations
Vittoria Vineis, Matteo Silvestri, Lorenzo Antonelli +2
Explainable Artificial Intelligence (XAI) seeks to enhance the transparency and accountability of machine learning systems, yet most methods follow a one-size-fits-all paradigm tha…
Enhancing XAI Narratives through Multi-Narrative Refinement and Knowledge Distillation
Flavio Giorgi, Matteo Silvestri, Cesare Campagnano +2
Explainable Artificial Intelligence has become a crucial area of research, aiming to demystify the decision-making processes of deep learning models. Among various explainability t…
Evading Overlapping Community Detection via Proxy Node Injection
Dario Loi, Matteo Silvestri, Fabrizio Silvestri +1
Protecting privacy in social graphs requires preventing sensitive information, such as community affiliations, from being inferred by graph analysis, without substantially altering…
The Right to Hide: Masking Community Affiliation via Minimal Graph Rewiring
Matteo Silvestri, Edoardo Gabrielli, Fabrizio Silvestri +1
Protecting privacy in social graphs may require obscuring nodes' membership in sensitive communities. However, doing so without significantly disrupting the underlying graph topolo…