English

Uncovering Hidden Intentions: Exploring Prompt Recovery for Deeper Insights into Generated Texts

Computation and Language 2024-06-25 v1 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.2406.15871,
  title  = {Uncovering Hidden Intentions: Exploring Prompt Recovery for Deeper Insights into Generated Texts},
  author = {Louis Give and Timo Zaoral and Maria Antonietta Bruno},
  journal= {arXiv preprint arXiv:2406.15871},
  year   = {2024}
}

Comments

Accepted at WNNLP 2024