Emotional prompting amplifies disinformation generation in AI large language models

Our study reveals that all tested LLMs effectively generate disinformation. Notably, emotional prompting had a significant impact on disinformation production rates, with models showing higher success rates when prompted with polite language compared to neutral or impolite requests. Our investigation highlights that LLMs can be exploited to create disinformation and emphasizes the critical need for ethics-by-design approaches in developing AI technologies. We maintain that identifying ways to mitigate the exploitation of LLMs through emotional prompting is crucial to prevent their misuse for purposes detrimental to public health and society.