12 papers
Rethinking GNNs and Missing Features: Challenges, Evaluation and a Robust Solution
Francesco Ferrini, Veronica Lachi, Antonio Longa +5
Handling missing node features is a key challenge for deploying Graph Neural Networks (GNNs) in real-world domains such as healthcare and sensor networks. Existing studies mostly a…
GNN Explanations that do not Explain and How to find Them
Steve Azzolin, Stefano Teso, Bruno Lepri +2
Explanations provided by Self-explainable Graph Neural Networks (SE-GNNs) are fundamental for understanding the model's inner workings and for identifying potential misuse of sensi…
SokoBench: Evaluating Long-Horizon Planning and Reasoning in Large Language Models
Sebastiano Monti, Carlo Nicolini, Gianni Pellegrini +2
Although the capabilities of large language models have been increasingly tested on complex reasoning tasks, their long-horizon planning abilities have not yet been extensively inv…
Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures
Marco Bronzini, Carlo Nicolini, Bruno Lepri +2
Despite their capabilities, Large Language Models (LLMs) remain opaque with limited understanding of their internal representations. Current interpretability methods either focus o…
I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy
Gian Maria Campedelli, Nicolò Penzo, Massimo Stefan +4
As LLM-based agents become increasingly autonomous and will more freely interact with each other, studying the interplay among them becomes crucial to anticipate emergent phenomena…
To Ask or Not to Ask: Learning to Require Human Feedback
Andrea Pugnana, Giovanni De Toni, Cesare Barbera +3
Developing decision-support systems that complement human performance in classification tasks remains an open challenge. A popular approach, Learning to Defer (LtD), allows a Machi…