How Susceptible are Large Language Models to Ideological Manipulation?

Understand

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 ideology of LLMs.