Date created: | Last Updated:

Category: Project

Description: The present study investigates the impact of tone and impersonation on the production of synthetic disinformation using Large Language Models (LLMs). The study examines three different prompt tones (polite, neutral, impolite) using two LLMs (text-davinci-002 and text-davinci-003) to evaluate the impact of tone and impersonation on disinformation production, on a range of 11 different topics. The results of this study could provide insights into the role of tone and impersonation in generating synthetic disinformation and its implications for the prevention and detection of disinformation campaigns. The wiki contains extensive documentation, both on the study and on the code + data included in the repository. Give it a look if need be.