5 papers
Explaining AI Agents Through Execution Traces
Vittoria Vineis, Fabiano Veglianti, Lorenzo Antonelli +3
AI Agents are increasingly deployed in real-world settings, where they interact with external tools and make sequential decisions with limited human oversight. This creates a press…
Optimizing Byzantine Node Placement in Decentralized Federated Learning
Edoardo Gabrielli, Gabriele Tolomei
Security evaluations of decentralized federated learning (DFL) typically focus on how Byzantine participants behave, while largely overlooking which participants are compromised. Y…
TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation
Ziheng Chen, Jiali Cheng, Zezhong Fan +4
Generative recommendation formulates next-item prediction as autoregressive generation over semantic ID (SID) sequences derived from users' historical interactions, making modern r…
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…
Counterfactual Explanations for Hypergraph Neural Networks
Fabiano Veglianti, Lorenzo Antonelli, Gabriele Tolomei
Hypergraph neural networks (HGNNs) effectively model higher-order interactions in many real-world systems but remain difficult to interpret, limiting their deployment in high-stake…