2 papers
cs.CL2025
Personal Attribute Leakage in Federated Speech Models
Hamdan Al-Ali, Ali Reza Ghavamipour, Tommaso Caselli +3
Federated learning is a common method for privacy-preserving training of machine learning models. In this paper, we analyze the vulnerability of ASR models to attribute inference a…
cs.CL2025
Simulating Identity, Propagating Bias: Abstraction and Stereotypes in LLM-Generated Text
Pia Sommerauer, Giulia Rambelli, Tommaso Caselli
Persona-prompting is a growing strategy to steer LLMs toward simulating particular perspectives or linguistic styles through the lens of a specified identity. While this method is…