mlsanityData to 7 Oct 2026

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

arXiv 2406.15871 ↗First posted 22 Jun 2024cs.CL cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 11 of its 20 references that are in the map. First posted on arXiv 22 Jun 2024.

Builds on

11 of 20 references.

References · 11

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  3. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  5. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  6. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  7. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  8. 2019Defending Against Neural Fake Newscited by 553
  9. 2021A Survey of Data Augmentation Approaches for NLPcited by 408
  10. 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
  11. 2019Generating Sentiment-Preserving Fake Online Reviews Using Neural Language Models and Their Human- and Machine-based Detectioncited by 50

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025StyleRec: A Benchmark Dataset for Prompt Recovery in Writing Style Transformationcited by 2
  2. 2025GPT, But Backwards: Exactly Inverting Language Model Outputscited by 2