Emotional Manipulation Through Prompt Engineering Amplifies Disinformation Generation in AI Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911790076526592 |
|---|---|
| author | Vinay, Rasita Spitale, Giovanni Biller-Andorno, Nikola Germani, Federico |
| author_facet | Vinay, Rasita Spitale, Giovanni Biller-Andorno, Nikola Germani, Federico |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_03550 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Emotional Manipulation Through Prompt Engineering Amplifies Disinformation Generation in AI Large Language Models Vinay, Rasita Spitale, Giovanni Biller-Andorno, Nikola Germani, Federico Artificial Intelligence Computers and Society Human-Computer Interaction 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. |
| title | Emotional Manipulation Through Prompt Engineering Amplifies Disinformation Generation in AI Large Language Models |
| topic | Artificial Intelligence Computers and Society Human-Computer Interaction |
| url | https://arxiv.org/abs/2403.03550 |