5 papers
Diagnosing GNN Failure Modes with Layer-Wise Probe Entropy
Shanzi Bao, Mar Gonzàlez I Català, Pietro Liò
Graph neural networks (GNNs) are typically evaluated only at their final layer, obscuring how task-relevant information evolves during message passing. We introduce a post-hoc diag…
Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoning
Mar Gonzàlez I Català, Haitz Sáez de Ocáriz Borde, Davide Murari +3
Chain-of-thought reasoning provides a structured computation between a model's input and final answer. Yet it is often evaluated through endpoint accuracy, which ignores the path t…
Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
Brown Zaz, Mar Gonzàlez I Català, Ferran Hernandez Caralt +2
In the transductive setting, where the full graph is observed but node labels are only partially available, progress in semi-supervised node classification has largely focused on a…
The Stepwise Informativeness Assumption: When Do Entropy Dynamics Track Reasoning Correctness in LLMs?
Mar Gonzàlez I Català, Haitz Sáez de Ocáriz Borde, George D. Montañez +1
Recent work uses entropy-based signals at multiple representation levels to study reasoning in large language models, but the field remains largely empirical. From a theoretical pe…
On the Necessity of Learnable Sheaf Laplacians
Ferran Hernandez Caralt, Mar Gonzàlez i Català, Adrián Bazaga +1
Sheaf Neural Networks (SNNs) were introduced as an extension of Graph Convolutional Networks to address oversmoothing on heterophilous graphs by attaching a sheaf to the input grap…