7 papers
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…
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…
You Don't Bring Me Flowers: Mitigating Unwanted Recommendations Through Conformal Risk Control
Giovanni De Toni, Erasmo Purificato, Emilia Gómez +3
Recommenders are significantly shaping online information consumption. While effective at personalizing content, these systems increasingly face criticism for propagating irrelevan…
GNNs Meet Sequence Models Along the Shortest-Path: an Expressive Method for Link Prediction
Francesco Ferrini, Veronica Lachi, Antonio Longa +2
Graph Neural Networks (GNNs) often struggle to capture the link-specific structural patterns crucial for accurate link prediction, as their node-centric message-passing schemes ove…
Community Aware Temporal Network Generation
Nicolò Alessandro Girardini, Antonio Longa, Gaia Trebucchi +3
The advantages of temporal networks in capturing complex dynamics, such as diffusion and contagion, has led to breakthroughs in real world systems across numerous fields. In the ca…
Unveiling LLMs: The Evolution of Latent Representations in a Dynamic Knowledge Graph
Marco Bronzini, Carlo Nicolini, Bruno Lepri +2
Large Language Models (LLMs) demonstrate an impressive capacity to recall a vast range of factual knowledge. However, understanding their underlying reasoning and internal mechanis…