3 papers
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…
cs.CL2025
How Humans and LLMs Organize Conceptual Knowledge: Exploring Subordinate Categories in Italian
Andrea Pedrotti, Giulia Rambelli, Caterina Villani +1
People can categorize the same entity at multiple taxonomic levels, such as basic (bear), superordinate (animal), and subordinate (grizzly bear). While prior research has focused o…
cs.CL2024
Annotating Constructions with UD: the experience of the Italian Constructicon
Ludovica Pannitto, Beatrice Bernasconi, Lucia Busso +3
The paper descirbes a first attempt of linking the Italian constructicon to UD resources