Fabrizio Silvestri

Large language models exhibit a critical vulnerability to distractor interference in retrieval-augmented contexts: they fail to prioritize relevant, factually correct documents over topically similar but misleading content. We introduce Lat-Defuse, a mechanistic framework that corrects this failu...

Masked Diffusion Language Models (DLMs) have recently emerged as a promising alternative to traditional Autoregressive Models (ARMs). DLMs employ transformer encoders with bidirectional attention, enabling parallel token generation while maintaining competitive performance. Although their efficie...

Modern sequential recommendation systems often rely on negative sampling to efficiently train models over vast item corpora. However, common strategies such as uniform, popularity-based sampling, or hard-negative mining, often yield uninformative negatives, introduce popularity bias, or suffer fr...

We introduce a load-aware selective embedding-pruning method to be used in dense retrieval systems. Our method adapts the embedding dimensionality at inference time based on per-query deadlines and the current queue occupancy. Under light load, full-dimensional embeddings maximise effectiveness;...