Fabrizio Frasca

Latest

• Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions
• Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT
• Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality
• Analyzing Large Language Models by Learning on Token Distribution Sequences
• Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity
• A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening
• Future Directions in Foundations of Graph Machine Learning
• Graph Positional Encoding via Random Feature Propagation