Large Language Models Reveal Information Operation Goals, Tactics, and Narrative Frames

arXiv:2405.03688v1 Announce Type: cross
Abstract: Adversarial information operations can destabilize societies by undermining fair elections, manipulating public opinions on policies, and promoting scams. Despite their widespread occurrence and potential impacts, our understanding of influence campaigns is limited by manual analysis of messages and subjective interpretation of their observable behavior. In this paper, we explore whether these limitations can be mitigated with large language models (LLMs), using GPT-3.5 as a case-study for coordinated campaign annotation. We first use GPT-3.5 to scrutinize …

abstract adversarial analysis arxiv behavior campaigns cs.cl cs.lg elections fair impacts influence information interpretation language language models large language large language models messages narrative observable operations opinions policies public scams tactics type understanding