Uncovering Hidden Intentions: Exploring Prompt Recovery for Deeper Insights into Generated Texts
This addresses the need for deeper insights into AI-generated content, though it is an incremental step as it focuses on a single model and initial exploration.
The paper tackles the problem of recovering the prompt used to generate AI-generated text, beyond mere detection, and finds that it is possible to achieve this with reasonable accuracy using methods like zero-shot and few-shot learning.
Today, the detection of AI-generated content is receiving more and more attention. Our idea is to go beyond detection and try to recover the prompt used to generate a text. This paper, to the best of our knowledge, introduces the first investigation in this particular domain without a closed set of tasks. Our goal is to study if this approach is promising. We experiment with zero-shot and few-shot in-context learning but also with LoRA fine-tuning. After that, we evaluate the benefits of using a semi-synthetic dataset. For this first study, we limit ourselves to text generated by a single model. The results show that it is possible to recover the original prompt with a reasonable degree of accuracy.