collaborators

6 papers

cs.LG2026

Exploring Geographic Relative Space in Large Language Models through Activation Patching

Stef De Sabbata, Rahul Baiju, Stefano Mizzaro +1

The increased use of Large Language Models (LLMs) in geography raises substantial questions about the safety of integrating these tools across a wide range of processes and analyse…

cs.IR2026

Beyond Seeing Is Believing: On Crowdsourced Detection of Audiovisual Deepfakes

Michael Soprano, Andrea Cioci, Stefano Mizzaro

Deepfakes are increasingly realistic and easy to produce, raising concerns about the reliability of human judgments in misinformation settings. We study audiovisual deepfake detect…

cs.IR2025

The Effect of Document Summarization on LLM-Based Relevance Judgments

Samaneh Mohtadi, Kevin Roitero, Stefano Mizzaro +1

Relevance judgments are central to the evaluation of Information Retrieval (IR) systems, but obtaining them from human annotators is costly and time-consuming. Large Language Model…

cs.CL2025

On Robustness and Reliability of Benchmark-Based Evaluation of LLMs

Riccardo Lunardi, Vincenzo Della Mea, Stefano Mizzaro +1

Large Language Models (LLMs) effectiveness is usually evaluated by means of benchmarks such as MMLU, ARC-C, or HellaSwag, where questions are presented in their original wording, t…

cs.LG2025

Geospatial Mechanistic Interpretability of Large Language Models

Stef De Sabbata, Stefano Mizzaro, Kevin Roitero

Large Language Models (LLMs) have demonstrated unprecedented capabilities across various natural language processing tasks. Their ability to process and generate viable text and co…

cs.IR2025

Efficiency and Effectiveness of LLM-Based Summarization of Evidence in Crowdsourced Fact-Checking

Kevin Roitero, Dustin Wright, Michael Soprano +2

Evaluating the truthfulness of online content is critical for combating misinformation. This study examines the efficiency and effectiveness of crowdsourced truthfulness assessment…