Marzio Di Vece

works on

brain connectivity 1 imbalance detection 1 information-theoretic benchmarks 1 signed networks 1 stochastic block model 1

From the 1 of 2 linked papers with an AI index.

collaborators

Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models

Martino Ciaperoni, Marzio Di Vece, Roberto Pellungrini +3

Large-scale foundation models exhibit behavioral shifts when subjected to interventions such as scaling, fine-tuning, reinforcement learning with human feedback, or in-context lear…