mlsanityData to 7 Oct 2026

StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements

arXiv 2408.15666 ↗First posted 28 Aug 2024cs.CLcited by 18

Not on the map. Why?

Abstract (arXiv)

Authorship obfuscation, rewriting a text to intentionally obscure the identity of the author, is an important but challenging task. Current methods using large language models (LLMs) lack interpretability and controllability, often ignoring author-specific stylistic features, resulting in less robust performance overall. To address this, we develop StyleRemix, an adaptive and interpretable obfuscation method that perturbs specific, fine-grained style elements of the original input text. StyleRemix uses pre-trained Low Rank Adaptation (LoRA) modules to rewrite an input specifically along various stylistic axes (e.g., formality and length) while maintaining low computational cost. StyleRemix outperforms state-of-the-art baselines and much larger LLMs in a variety of domains as assessed by both automatic and human evaluation. Additionally, we release AuthorMix, a large set of 30K high-quality, long-form texts from a diverse set of 14 authors and 4 domains, and DiSC, a parallel corpus of 1,500 texts spanning seven style axes in 16 unique directions

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 37 of its 62 references that are in the map. First posted on arXiv 28 Aug 2024.

Builds on

37 of 62 references.

References · 37

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  6. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  7. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  8. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  9. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  10. 2018Neural Network Acceptability Judgmentscited by 952
  11. 2023TIES-Merging: Resolving Interference When Merging Modelscited by 795
  12. 2023Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunchcited by 679
25 more
  1. 2021Merging Models with Fisher-Weighted Averagingcited by 613
  2. 2020Beyond English-Centric Multilingual Machine Translationcited by 559
  3. 2017Learning multiple visual domains with residual adapterscited by 553
  4. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 434
  5. 2023LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Compositioncited by 359
  6. 2023Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Mergingcited by 271
  7. 2023Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewardscited by 232
  8. 2021BookSum: A Collection of Datasets for Long-form Narrative Summarizationcited by 184
  9. 2020Reformulating Unsupervised Style Transfer as Paraphrase Generationcited by 181
  10. 2023ZipIt! Merging Models from Different Tasks without Trainingcited by 178
  11. 2020Deep Learning for Text Style Transfer: A Surveycited by 161
  12. 2022Diverse Weight Averaging for Out-of-Distribution Generalizationcited by 148
  13. 2020NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraintscited by 146
  14. 2017Style Transfer in Text: Exploration and Evaluationcited by 145
  15. 2021TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generationcited by 118
  16. 2018Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approachcited by 55
  17. 2017A4NT: Author Attribute Anonymity by Adversarial Training of Neural Machine Translationcited by 41
  18. 2023Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuningcited by 33
  19. 2023Don't lose the message while paraphrasing: A study on content preserving style transfercited by 25
  20. 2020Versatile Black-Box Optimizationcited by 22
  21. 2022Are You Robert or RoBERTa? Deceiving Online Authorship Attribution Models Using Neural Text Generatorscited by 14
  22. 2023STEER: Unified Style Transfer with Expert Reinforcementcited by 14
  23. 2021Avengers Ensemble! Improving Transferability of Authorship Obfuscationcited by 7
  24. 2024JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Modelscited by 7
  25. 2024Style Transfer with Multi-iteration Preference Optimizationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 9; 2026: 8.

18 papers.

Sort:

By area:

  1. 2024StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examplescited by 32
  2. 2025Personalized Text Generation with Contrastive Activation Steeringcited by 30
  3. 2025Leveraging Multilingual Training for Authorship Representation: Enhancing Generalization across Languages and Domainscited by 7
  4. 2025HyPerAlign: Interpretable Personalized LLM Alignment via Hypothesis Generationcited by 6
  5. 2025Steering Large Language Models with Register Analysis for Arbitrary Style Transfercited by 5
  6. 2025FedMerge: Federated Personalization via Model Mergingcited by 4
  7. 2025Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymizationcited by 4
  8. 2025Unraveling Interwoven Roles of Large Language Models in Authorship Privacy: Obfuscation, Mimicking, and Verificationcited by 2
  9. 2026AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixingcited by 1
  10. 2025Personalized Author Obfuscation with Large Language Modelscited by 0
  11. 2025RL-Finetuned LLMs for Privacy-Preserving Synthetic Rewritingcited by 0
  12. 2026Interpreting Style Representations via Style-Eliciting Promptscited by 0
6 more
  1. 2026Occluded Oculus: Operationalizing Stylistic Obscurementcited by 0
  2. 2026Small Is Enough: Per-User Style Rewriting of AI-Edited Text via LoRA Adapterscited by 0
  3. 2026Introducing the Privacy-HSD Trade-off: Hate Speech Detection, but not at the Cost of Privacycited by 0
  4. 2026Aggregation-Aware Synthetic Text Generation Against Authorship Re-Identificationcited by 0
  5. 2026I Am No One: Style-Aware Paraphrasing for Text Anonymizationcited by 0
  6. 2026Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Modelscited by 0