How Susceptible are Large Language Models to Ideological Manipulation?

arXiv:2402.11725v1 Announce Type: cross
Abstract: Large Language Models (LLMs) possess the potential to exert substantial influence on public perceptions and interactions with information. This raises concerns about the societal impact that could arise if the ideologies within these models can be easily manipulated. In this work, we investigate how effectively LLMs can learn and generalize ideological biases from their instruction-tuning data. Our findings reveal a concerning vulnerability: exposure to only a small amount of ideologically driven samples significantly alters the …

arxiv can cs.cl cs.cr cs.cy effectively impact influence information language language models large llms manipulation public societal impact work