All Stories

  1. Impersonating the Crowd: Evaluating LLMs' Ability to Replicate Human Judgment in Misinformation Assessment

    Article • July 2025, ACM (Association for Computing Machinery)

    Kevin Roitero, Riccardo Lunardi

  2. PILs of Knowledge: A Synthetic Benchmark for Evaluating Question Answering Systems in Healthcare

    Article • July 2025, ACM (Association for Computing Machinery)

    Riccardo Lunardi, Kevin Roitero, Michael Soprano

  3. Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas

    Article • May 2025, ACM (Association for Computing Machinery)

    Riccardo Lunardi, Kevin Roitero, Gianluca Demartini

  4. The Elusiveness of Detecting Political Bias in Language Models: The Impact of Question Wording

    Article • October 2024, ACM (Association for Computing Machinery)

    Kevin Roitero, Riccardo Lunardi