11 papers
AMAQA: A Metadata-based QA Dataset for RAG Systems
Davide Bruni, Marco Avvenuti, Nicola Tonellotto +1
Retrieval-augmented generation (RAG) systems are widely used in question-answering (QA) tasks, but current benchmarks lack metadata integration, limiting their evaluation in scenar…
Assessing the Reliability of Persona-Conditioned LLMs as Synthetic Survey Respondents
Erika Elizabeth Taday Morocho, Lorenzo Cima, Tiziano Fagni +2
Using persona-conditioned LLMs as synthetic survey respondents has become a common practice in computational social science and agent-based simulations. Yet, it remains unclear whe…
Beyond Trial-and-Error: Predicting User Abandonment After a Moderation Intervention
Benedetta Tessa, Lorenzo Cima, Amaury Trujillo +2
Current content moderation follows a reactive, trial-and-error approach, where interventions are applied and their effects are only measured post-hoc. In contrast, we introduce a p…
JPEGs Just Got Snipped: Croppable Signatures Against Deepfake Images
Pericle Perazzo, Massimiliano Mattei, Giuseppe Anastasi +4
Deepfakes are a type of synthetic media created using artificial intelligence, specifically deep learning algorithms. This technology can for example superimpose faces and voices o…
Investigating the heterogenous effects of a massive content moderation intervention via Difference-in-Differences
Lorenzo Cima, Benedetta Tessa, Stefano Cresci +2
In today's online environments, users encounter harm and abuse on a daily basis. Therefore, content moderation is crucial to ensure their safety and well-being. However, the effect…
Human and LLM Biases in Hate Speech Annotations: A Socio-Demographic Analysis of Annotators and Targets
Tommaso Giorgi, Lorenzo Cima, Tiziano Fagni +2
The rise of online platforms exacerbated the spread of hate speech, demanding scalable and effective detection. However, the accuracy of hate speech detection systems heavily relie…