mlsanityData to 7 Oct 2026

DORY: Deliberative Prompt Recovery for LLM

arXiv 2405.20657 ↗First posted 31 May 2024cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

Prompt recovery in large language models (LLMs) is crucial for understanding how LLMs work and addressing concerns regarding privacy, copyright, etc. The trend towards inference-only APIs complicates this task by restricting access to essential outputs for recovery. To tackle this challenge, we extract prompt-related information from limited outputs and identify a strong(negative) correlation between output probability-based uncertainty and the success of prompt recovery. This finding led to the development of Deliberative PrOmpt RecoverY (DORY), our novel approach that leverages uncertainty to recover prompts accurately. DORY involves reconstructing drafts from outputs, refining these with hints, and filtering out noise based on uncertainty. Our evaluation across diverse LLMs and prompt benchmarks shows that DORY outperforms existing baselines, improving performance by approximately 10.82% and establishing a new state-of-the-art record in prompt recovery tasks. Significantly, DORY operates using a single LLM without any external resources or model, offering a cost-effective, user-friendly prompt recovery solution.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 28 of its 46 references that are in the map. First posted on arXiv 31 May 2024.

Builds on

28 of 46 references.

References · 28

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2020Scaling Laws for Neural Language Modelscited by 6,411
  5. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  6. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  7. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  8. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,565
  9. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,326
  10. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
  11. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  12. 2016Stealing Machine Learning Models via Prediction APIscited by 602
16 more
  1. 2023GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Promptscited by 520
  2. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Studycited by 478
  3. 2023The False Promise of Imitating Proprietary LLMscited by 254
  4. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 241
  5. 2023Language Modeling Is Compressioncited by 225
  6. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 189
  7. 2023Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigationscited by 157
  8. 2023Privacy Auditing with One (1) Training Runcited by 119
  9. 2017Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a surveycited by 90
  10. 2023Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentencecited by 81
  11. 2020Imitation Attacks and Defenses for Black-box Machine Translation Systemscited by 78
  12. 2023Jailbreaking GPT-4V via Self-Adversarial Attacks with System Promptscited by 62
  13. 2022Text Revealer: Private Text Reconstruction via Model Inversion Attacks against Transformerscited by 28
  14. 2023Label-Only Model Inversion Attacks via Knowledge Transfercited by 21
  15. 2024RECOST: External Knowledge Guided Data-efficient Instruction Tuningcited by 18
  16. 2022Distill the Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translationcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 3.

7 papers.

  1. 2026RAGEN-2: Reasoning Collapse in Agentic RLcited by 16
  2. 2025Better Language Model Inversion by Compactly Representing Next-Token Distributionscited by 9
  3. 2026LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systemscited by 6
  4. 2025StyleRec: A Benchmark Dataset for Prompt Recovery in Writing Style Transformationcited by 2
  5. 2025GPT, But Backwards: Exactly Inverting Language Model Outputscited by 2
  6. 2024Confidential Prompting: Privacy-preserving LLM Inference on Cloudcited by 1
  7. 2026PANOPTICON: A PII-Based Assemblage of Naturalistic Output Tokens for Investigating Privacy Leakage Within LLM Context Windowcited by 0