14 citations · 14 across the 5 of their papers we have counts for
6 papers
A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering
Gianluca Bonifazi, Christopher Buratti, Michele Marchetti +5
Retrieval-Augmented Generation (RAG) systems for multi-hop Question Answering (QA) must balance retrieval quality with computational cost. This cost is incurred during indexing tim…
Latent Trajectory Discrimination for AI-Generated Text Detection
Gianluca Bonifazi, Christopher Buratti, Michele Marchetti +5
Most existing approaches to AI-Generated Text Detection (AIGTD) treat documents as static objects and base their decisions on aggregate statistics or globally compressed embeddings…
Gradient-Skipping Relevance Propagation for Efficient Explainability of Vision Transformers
Christopher Buratti, Michele Marchetti, Federica Parlapiano +3
Vision Transformers (ViTs) are difficult to interpret because current methods of relevance propagation and attention flow do not fully consider some key architectural features, suc…
Efficient Retrieval-Augmented Generation via Token Co-occurrence Graphs
Gianluca Bonifazi, Christopher Buratti, Michele Marchetti +5
Retrieval-Augmented Generation (RAG) mitigates hallucinations in Large Language Models (LLMs) by grounding the generation process on external knowledge. However, standard RAG appro…
Characterizing Information Shared by Participants to Coding Challenges: The Case of Advent of Code
Francesco Cauteruccio, Enrico Corradini, Luca Virgili
Advent of Code (AoC from now on) is a popular coding challenge requiring to solve programming puzzles for a variety of skill sets and levels. AoC follows the advent calendar, there…
Predicting Tweet Engagement with Graph Neural Networks
Marco Arazzi, Marco Cotogni, Antonino Nocera +1
Social Networks represent one of the most important online sources to share content across a world-scale audience. In this context, predicting whether a post will have any impact i…