Emotional Manipulation Through Prompt Engineering Amplifies Disinformation Generation in AI Large Language Models

TL;DR

This paper demonstrates that OpenAI's large language models can generate disinformation effectively when prompted emotionally, highlighting their potential misuse and the importance of responsible AI development.

Contribution

It reveals how emotional prompt engineering amplifies disinformation generation in LLMs and compares their responses to polite versus impolite prompts.

Findings

All tested LLMs can produce disinformation successfully.

Emotional prompting influences the frequency of disinformation generation.

Polite prompts lead to high disinformation output, impolite prompts reduce it.

Abstract

This study investigates the generation of synthetic disinformation by OpenAI's Large Language Models (LLMs) through prompt engineering and explores their responsiveness to emotional prompting. Leveraging various LLM iterations using davinci-002, davinci-003, gpt-3.5-turbo and gpt-4, we designed experiments to assess their success in producing disinformation. Our findings, based on a corpus of 19,800 synthetic disinformation social media posts, reveal that all LLMs by OpenAI can successfully produce disinformation, and that they effectively respond to emotional prompting, indicating their nuanced understanding of emotional cues in text generation. When prompted politely, all examined LLMs consistently generate disinformation at a high frequency. Conversely, when prompted impolitely, the frequency of disinformation production diminishes, as the models often refuse to generate disinformation and instead caution users that the tool is not intended for such purposes. This research contributes to the ongoing discourse surrounding responsible development and application of AI technologies, particularly in mitigating the spread of disinformation and promoting transparency in AI-generated content.