Are Paraphrases Generated by Large Language Models Invertible?

• URL: http://arxiv.org/abs/2410.21637v1
• Date: Tue, 29 Oct 2024 00:46:24 GMT
• Title: Are Paraphrases Generated by Large Language Models Invertible?
• Authors: Rafael Rivera Soto, Barry Chen, Nicholas Andrews,
• Abstract summary: We consider the problem of paraphrase inversion: given a paraphrased document, attempt to recover the original text. We fine-tune paraphrase inversion models, both with and without additional author-specific context. We show that, when starting from paraphrased machine-generated text, we can recover significant portions of the document using a learned inversion model.
• Score: 4.148732457277201
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models can produce highly fluent paraphrases while retaining much of the original meaning. While this capability has a variety of helpful applications, it may also be abused by bad actors, for example to plagiarize content or to conceal their identity. This motivates us to consider the problem of paraphrase inversion: given a paraphrased document, attempt to recover the original text. To explore the feasibility of this task, we fine-tune paraphrase inversion models, both with and without additional author-specific context to help guide the inversion process. We explore two approaches to author-specific inversion: one using in-context examples of the target author's writing, and another using learned style representations that capture distinctive features of the author's style. We show that, when starting from paraphrased machine-generated text, we can recover significant portions of the document using a learned inversion model. When starting from human-written text, the variety of source writing styles poses a greater challenge for invertability. However, even when the original tokens can't be recovered, we find the inverted text is stylistically similar to the original, which significantly improves the performance of plagiarism detectors and authorship identification systems that rely on stylistic markers.

Related papers

• Detecting Document-level Paraphrased Machine Generated Content: Mimicking Human Writing Style and Involving Discourse Features [57.34477506004105]
  Machine-generated content poses challenges such as academic plagiarism and the spread of misinformation. We introduce novel methodologies and datasets to overcome these challenges. We propose MhBART, an encoder-decoder model designed to emulate human writing style. We also propose DTransformer, a model that integrates discourse analysis through PDTB preprocessing to encode structural features.
  arXiv  Detail & Related papers  (2024-12-17T08:47:41Z)
• RKadiyala at SemEval-2024 Task 8: Black-Box Word-Level Text Boundary Detection in Partially Machine Generated Texts [0.0]
  This paper introduces few reliable approaches for identifying which part of a given text is machine generated at a word level. We present a comparison with proprietary systems, performance of our model on unseen domains' and generators' texts. The findings reveal significant improvements in detection accuracy along with comparison on other aspects of detection capabilities.
  arXiv  Detail & Related papers  (2024-10-22T03:21:59Z)
• Detecting Machine-Generated Long-Form Content with Latent-Space Variables [54.07946647012579]
  Existing zero-shot detectors primarily focus on token-level distributions, which are vulnerable to real-world domain shifts. We propose a more robust method that incorporates abstract elements, such as event transitions, as key deciding factors to detect machine versus human texts.
  arXiv  Detail & Related papers  (2024-10-04T18:42:09Z)
• Forging the Forger: An Attempt to Improve Authorship Verification via Data Augmentation [52.72682366640554]
  Authorship Verification (AV) is a text classification task concerned with inferring whether a candidate text has been written by one specific author or by someone else. It has been shown that many AV systems are vulnerable to adversarial attacks, where a malicious author actively tries to fool the classifier by either concealing their writing style, or by imitating the style of another author.
  arXiv  Detail & Related papers  (2024-03-17T16:36:26Z)
• Retrieval is Accurate Generation [99.24267226311157]
  We introduce a novel method that selects context-aware phrases from a collection of supporting documents. Our model achieves the best performance and the lowest latency among several retrieval-augmented baselines.
  arXiv  Detail & Related papers  (2024-02-27T14:16:19Z)
• Paraphrase Types for Generation and Detection [7.800428507692341]
  We name these tasks Paraphrase Type Generation and Paraphrase Type Detection. Our results suggest that while current techniques perform well in a binary classification scenario, the inclusion of fine-grained paraphrase types poses a significant challenge. We believe paraphrase types can unlock a new paradigm for developing paraphrase models and solving tasks in the future.
  arXiv  Detail & Related papers  (2023-10-23T12:32:41Z)
• ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation [59.91139600152296]
  ParaAMR is a large-scale syntactically diverse paraphrase dataset created by abstract meaning representation back-translation. We show that ParaAMR can be used to improve on three NLP tasks: learning sentence embeddings, syntactically controlled paraphrase generation, and data augmentation for few-shot learning.
  arXiv  Detail & Related papers  (2023-05-26T02:27:33Z)
• Smaller Language Models are Better Black-box Machine-Generated Text Detectors [56.36291277897995]
  Small and partially-trained models are better universal text detectors. We find that whether the detector and generator were trained on the same data is not critically important to the detection success. For instance, the OPT-125M model has an AUC of 0.81 in detecting ChatGPT generations, whereas a larger model from the GPT family, GPTJ-6B, has AUC of 0.45.
  arXiv  Detail & Related papers  (2023-05-17T00:09:08Z)
• Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense [56.077252790310176]
  We present a paraphrase generation model (DIPPER) that can paraphrase paragraphs, condition on surrounding context, and control lexical diversity and content reordering. Using DIPPER to paraphrase text generated by three large language models (including GPT3.5-davinci-003) successfully evades several detectors, including watermarking. We introduce a simple defense that relies on retrieving semantically-similar generations and must be maintained by a language model API provider.
  arXiv  Detail & Related papers  (2023-03-23T16:29:27Z)
• Paraphrase Identification with Deep Learning: A Review of Datasets and Methods [1.4325734372991794]
  We investigate how the under-representation of certain paraphrase types in popular datasets affects the ability to detect plagiarism. We introduce and validate a new refined typology for paraphrases. We propose new directions for future research and dataset development to enhance AI-based paraphrase detection.
  arXiv  Detail & Related papers  (2022-12-13T23:06:20Z)
• PART: Pre-trained Authorship Representation Transformer [64.78260098263489]
  Authors writing documents imprint identifying information within their texts: vocabulary, registry, punctuation, misspellings, or even emoji usage. Previous works use hand-crafted features or classification tasks to train their authorship models, leading to poor performance on out-of-domain authors. We propose a contrastively trained model fit to learn textbfauthorship embeddings instead of semantics.
  arXiv  Detail & Related papers  (2022-09-30T11:08:39Z)
• Text Revealer: Private Text Reconstruction via Model Inversion Attacks against Transformers [22.491785618530397]
  We formulate emphText Revealer -- the first model inversion attack for text reconstruction against text classification with transformers. Our attacks faithfully reconstruct private texts included in training data with access to the target model. Our experiments demonstrate that our attacks are effective for datasets with different text lengths and can reconstruct private texts with accuracy.
  arXiv  Detail & Related papers  (2022-09-21T17:05:12Z)
• SynSciPass: detecting appropriate uses of scientific text generation [0.0]
  We develop a framework for dataset development that provides a nuanced approach to detecting machine generated text. By training the same model that performed well on DAGPap22 on SynSciPass, we show that not only is the model more robust to domain shifts but also is able to uncover the type of technology used for machine generated text.
  arXiv  Detail & Related papers  (2022-09-07T13:16:40Z)
• Letter-level Online Writer Identification [86.13203975836556]
  We focus on a novel problem, letter-level online writer-id, which requires only a few trajectories of written letters as identification cues. A main challenge is that a person often writes a letter in different styles from time to time. We refer to this problem as the variance of online writing styles (Var-O-Styles)
  arXiv  Detail & Related papers  (2021-12-06T07:21:53Z)
• InvBERT: Text Reconstruction from Contextualized Embeddings used for Derived Text Formats of Literary Works [1.6058099298620423]
  Digital Humanities and Computational Literary Studies apply text mining methods to investigate literature. Due to copyright restrictions, the availability of relevant digitized literary works is limited. Our attempts to invert BERT suggest, that publishing parts of the encoder together with the contextualized embeddings is critical.
  arXiv  Detail & Related papers  (2021-09-21T11:35:41Z)
• Towards Document-Level Paraphrase Generation with Sentence Rewriting and Reordering [88.08581016329398]
  We propose CoRPG (Coherence Relationship guided Paraphrase Generation) for document-level paraphrase generation. We use graph GRU to encode the coherence relationship graph and get the coherence-aware representation for each sentence. Our model can generate document paraphrase with more diversity and semantic preservation.
  arXiv  Detail & Related papers  (2021-09-15T05:53:40Z)
• Exemplar-Controllable Paraphrasing and Translation using Bitext [57.92051459102902]
  We adapt models from prior work to be able to learn solely from bilingual text (bitext) Our single proposed model can perform four tasks: controlled paraphrase generation in both languages and controlled machine translation in both language directions.
  arXiv  Detail & Related papers  (2020-10-12T17:02:50Z)
• Don't Change Me! User-Controllable Selective Paraphrase Generation [45.0436584774495]
  In paraphrase generation, source sentences often contain phrases that should not be altered. Our solution is to provide the user with explicit tags that can be placed around any arbitrary segment of text to mean "don't change me!" The contribution of this work is a novel data generation technique using distant supervision.
  arXiv  Detail & Related papers  (2020-08-21T03:31:50Z)
• Neural Syntactic Preordering for Controlled Paraphrase Generation [57.5316011554622]
  Our work uses syntactic transformations to softly "reorder'' the source sentence and guide our neural paraphrasing model. First, given an input sentence, we derive a set of feasible syntactic rearrangements using an encoder-decoder model. Next, we use each proposed rearrangement to produce a sequence of position embeddings, which encourages our final encoder-decoder paraphrase model to attend to the source words in a particular order.
  arXiv  Detail & Related papers  (2020-05-05T09:02:25Z)
• A Multi-cascaded Model with Data Augmentation for Enhanced Paraphrase Detection in Short Texts [1.6758573326215689]
  We present a data augmentation strategy and a multi-cascaded model for improved paraphrase detection in short texts. Our model is both wide and deep and provides greater robustness across clean and noisy short texts.
  arXiv  Detail & Related papers  (2019-12-27T12:10:10Z)

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.