Do Androids Dream of Unseen Puppeteers? Probing for a Conspiracy Tendencies in Large Language Models
Read the original on arXiv Computation and Language →The paper examines whether large language models (LLMs) exhibit conspiratorial tendencies, socio-demographic biases in this domain, and how easily they can be conditioned to adopt conspiratorial viewpoints. Using validated psychometric surveys, the authors find that LLMs partially align with conspiracy beliefs, that conditioning with demographic attributes yields uneven effects revealing latent biases, and that targeted prompts can readily shift responses toward conspiratorial stances. These findings underscore the vulnerability of LLMs to manipulation and the potential risks of deploying them in sensitive contexts.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.