mlsanityData to 13 Oct 2026

ParaGuide: Guided Diffusion Paraphrasers for Plug-and-Play Textual Style Transfer

arXiv 2308.15459 ↗First posted 29 Aug 2023cs.CL cs.AIcited by 18

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

Textual style transfer is the task of transforming stylistic properties of text while preserving meaning. Target "styles" can be defined in numerous ways, ranging from single attributes (e.g, formality) to authorship (e.g, Shakespeare). Previous unsupervised style-transfer approaches generally rely on significant amounts of labeled data for only a fixed set of styles or require large language models. In contrast, we introduce a novel diffusion-based framework for general-purpose style transfer that can be flexibly adapted to arbitrary target styles at inference time. Our parameter-efficient approach, ParaGuide, leverages paraphrase-conditioned diffusion models alongside gradient-based guidance from both off-the-shelf classifiers and strong existing style embedders to transform the style of text while preserving semantic information. We validate the method on the Enron Email Corpus, with both human and automatic evaluations, and find that it outperforms strong baselines on formality, sentiment, and even authorship style transfer.

Key facts. Cited by 18 papers in the map (data through 13 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 40 of its 101 references that are in the map. First posted on arXiv 29 Aug 2023.

Builds on

40 of 101 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Palette: Image-to-Image Diffusion Models10 Nov

Other references · 39

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  2. 2020Language Models are Few-Shot Learnerscited by 32,320
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,952
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,223
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,549
  6. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,322
  7. 2020Denoising Diffusion Implicit Modelscited by 9,718
  8. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,107
  9. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,023
  10. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,360
  11. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,751
  12. 2019The Curious Case of Neural Text Degenerationcited by 2,893
27 more
  1. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
  2. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,012
  3. 2018Neural Network Acceptability Judgmentscited by 957
  4. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 797
  5. 2021Datasets: A Community Library for Natural Language Processingcited by 529
  6. 2020TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classificationcited by 416
  7. 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 378
  8. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 375
  9. 2022SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Controlcited by 191
  10. 2020Reformulating Unsupervised Style Transfer as Paraphrase Generationcited by 182
  11. 2020Deep Learning for Text Style Transfer: A Surveycited by 161
  12. 2023Likelihood-Based Diffusion Language Modelscited by 148
  13. 2022Self-conditioned Embedding Diffusion for Text Generationcited by 116
  14. 2021A Recipe For Arbitrary Text Style Transfer with Large Language Modelscited by 107
  15. 2023Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Taskscited by 103
  16. 2022Same Author or Just Same Topic? Towards Content-Independent Style Representationscited by 85
  17. 2021Controlled Text Generation as Continuous Optimization with Multiple Constraintscited by 70
  18. 2022Mix and Match: Learning-free Controllable Text Generation using Energy Language Modelscited by 66
  19. 2023TESS: Text-to-Text Self-Conditioned Simplex Diffusioncited by 64
  20. 2022SeqDiffuSeq: Text Diffusion with Encoder-Decoder Transformerscited by 63
  21. 2020PowerTransformer: Unsupervised Controllable Revision for Biased Language Correctioncited by 59
  22. 2021Text Detoxification using Large Pre-trained Neural Modelscited by 52
  23. 2021XFORMAL: A Benchmark for Multilingual Formality Style Transfercited by 51
  24. 2020TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restylingcited by 40
  25. 2020PySBD: Pragmatic Sentence Boundary Disambiguationcited by 38
  26. 2021A Deep Metric Learning Approach to Account Linkingcited by 24
  27. 2019Learning Invariant Representations of Social Media Userscited by 21

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 5; 2025: 6; 2026: 7.

18 papers.

Sort:

By area:

  1. 2025A General Framework for Inference-time Scaling and Steering of Diffusion Modelscited by 217
  2. 2025A Survey on Diffusion Language Modelscited by 77
  3. 2024StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examplescited by 34
  4. 2024TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddingscited by 17
  5. 2024Multilingual and Explainable Text Detoxification with Parallel Corporacited by 12
  6. 2024Learning from Many Voices: Literary MT Using Multi-Reference Human and Synthetic Datacited by 3
  7. 2025EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Modelscited by 3
  8. 2025Controllable Stylistic Text Generation with Train-Time Attribute-Regularized Diffusioncited by 2
  9. 2025Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Modelcited by 1
  10. 2026AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixingcited by 1
  11. 2024SAG: Style-Aligned Article Generation via Model Collaborationcited by 0
  12. 2025Attacks on Machine-Text Detectors Retain Stylistic Fingerprintscited by 0
6 more
  1. 2026RT-SFT: Text Style Transfer from Non-Parallel Corpora by Roundtrip Translationcited by 0
  2. 2026Guidance Is Not a Hyperparameter: Learning Dynamic Control in Diffusion Language Modelscited by 0
  3. 2026Interpreting Style Representations via Style-Eliciting Promptscited by 0
  4. 2026Speculative Refinement: A Hybrid Autoregressive Diffusion Decoding Strategy and Its Behavior Across Benchmarkscited by 0
  5. 2026STEB: Style Text Embedding Benchmarkcited by 0
  6. 2026HyperStyler: Low-resource Authorship Style Transfer via Context-aware Style Navigation and Hypernetworkscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Fine-grained Text Style Transfer with Diffusion-Based Language Models
  2. 2024FreeStyle: Free Lunch for Text-guided Style Transfer using Diffusion Models
  3. 2024DiffuseST: Unleashing the Capability of the Diffusion Model for Style Transfer
  4. 2025StyDeco: Unsupervised Style Transfer with Distilling Priors and Semantic Decoupling
  5. 2025Syntax-Guided Diffusion Language Models with User-Integrated Personalization
  6. 2026Stylistic Attribute Control in Latent Diffusion Models
  7. 2022Diffusion-based Image Translation using Disentangled Style and Content Representation
  8. 2026Predicting Steering Vectors and Adapter Weights for Few-Shot Author-Style Transfer