Reverse Prompt Engineering

• URL: http://arxiv.org/abs/2411.06729v1
• Date: Mon, 11 Nov 2024 05:58:48 GMT
• Title: Reverse Prompt Engineering
• Authors: Hanqing Li, Diego Klabjan,
• Abstract summary: This paper explores a new black-box, zero-shot language model inversion problem. It proposes an innovative framework for prompt reconstruction using only text outputs from a language model.
• Score: 12.46661880219403
• License:
• Abstract: This paper explores a new black-box, zero-shot language model inversion problem and proposes an innovative framework for prompt reconstruction using only text outputs from a language model. Leveraging a large language model alongside an optimization algorithm, the proposed method effectively recovers prompts with minimal resources. Experimental results on several datasets derived from public sources indicate that the proposed approach achieves high-quality prompt recovery and generates prompts more similar to the originals than current state-of-the-art methods. Additionally, the use-case study demonstrates the method's strong potential for generating high-quality text data.

Related papers

• Advancing Prompt Recovery in NLP: A Deep Dive into the Integration of Gemma-2b-it and Phi2 Models [18.936945999215038]
  The design and effectiveness of prompts represent a challenging and relatively untapped field within NLP research. This paper delves into an exhaustive investigation of prompt recovery methodologies, employing a spectrum of pre-trained language models and strategies. Through meticulous experimentation and detailed analysis, we elucidate the outstanding performance of the Gemma-2b-it + Phi2 model + Pretrain.
  arXiv  Detail & Related papers  (2024-07-07T02:15:26Z)
• Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation [16.35126275175784]
  This paper proposes a decision-boundary-aware data augmentation strategy to enhance robustness using pretrained language models. The proposed technique first focuses on shifting the latent features closer to the decision boundary, followed by reconstruction to generate an ambiguous version with a soft label.
  arXiv  Detail & Related papers  (2024-03-22T05:18:08Z)
• Evaluating Generative Ad Hoc Information Retrieval [58.800799175084286]
  generative retrieval systems often directly return a grounded generated text as a response to a query. Quantifying the utility of the textual responses is essential for appropriately evaluating such generative ad hoc retrieval.
  arXiv  Detail & Related papers  (2023-11-08T14:05:00Z)
• RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling [79.56442336234221]
  We introduce RegaVAE, a retrieval-augmented language model built upon the variational auto-encoder (VAE) It encodes the text corpus into a latent space, capturing current and future information from both source and target text. Experimental results on various datasets demonstrate significant improvements in text generation quality and hallucination removal.
  arXiv  Detail & Related papers  (2023-10-16T16:42:01Z)
• Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning [114.54944761345594]
  We present a novel approach for structured data-to-text generation that addresses the limitations of existing methods. Our proposed method aims to improve performance in multi-task training, zero-shot and few-shot scenarios.
  arXiv  Detail & Related papers  (2023-08-10T03:09:12Z)
• Boosting Event Extraction with Denoised Structure-to-Text Augmentation [52.21703002404442]
  Event extraction aims to recognize pre-defined event triggers and arguments from texts. Recent data augmentation methods often neglect the problem of grammatical incorrectness. We propose a denoised structure-to-text augmentation framework for event extraction DAEE.
  arXiv  Detail & Related papers  (2023-05-16T16:52:07Z)
• A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning [50.910152564914405]
  Existing posterior sampling methods for reinforcement learning are limited by being model-based or lack worst-case theoretical guarantees beyond linear MDPs. This paper proposes a new model-free formulation of posterior sampling that applies to more general episodic reinforcement learning problems with theoretical guarantees.
  arXiv  Detail & Related papers  (2022-08-23T12:21:01Z)
• A New Sentence Extraction Strategy for Unsupervised Extractive Summarization Methods [26.326800624948344]
  We model the task of extractive text summarization methods from the perspective of Information Theory. To improve the feature distribution and to decrease the mutual information of summarization sentences, we propose a new sentence extraction strategy.
  arXiv  Detail & Related papers  (2021-12-06T18:00:02Z)
• GQE-PRF: Generative Query Expansion with Pseudo-Relevance Feedback [8.142861977776256]
  We propose a novel approach which effectively integrates text generation models into PRF-based query expansion. Our approach generates augmented query terms via neural text generation models conditioned on both the initial query and pseudo-relevance feedback. We evaluate the performance of our approach on information retrieval tasks using two benchmark datasets.
  arXiv  Detail & Related papers  (2021-08-13T01:09:02Z)
• BERT-based Chinese Text Classification for Emergency Domain with a Novel Loss Function [9.028459232146474]
  This paper proposes an automatic Chinese text categorization method for solving the emergency event report classification problem. To overcome the data imbalance problem in the distribution of emergency event categories, a novel loss function is proposed to improve the performance of the BERT-based model. The proposed method has achieved the best performance in terms of accuracy, weighted-precision, weighted-recall, and weighted-F1 values.
  arXiv  Detail & Related papers  (2021-04-09T05:25:00Z)
• Improving Adversarial Text Generation by Modeling the Distant Future [155.83051741029732]
  We consider a text planning scheme and present a model-based imitation-learning approach to alleviate the aforementioned issues. We propose a novel guider network to focus on the generative process over a longer horizon, which can assist next-word prediction and provide intermediate rewards for generator optimization.
  arXiv  Detail & Related papers  (2020-05-04T05:45:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.