Papers
arxiv:2408.15666

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

Published on Aug 28
· Submitted by hallisky on Aug 30
Authors:
,
,

Abstract

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

Community

Paper author Paper submitter

The text introduces StyleRemix, a method for authorship obfuscation that modifies specific style elements of text for better control and interpretability, outperforming current models. It also presents two new datasets, AuthorMix and DiSC, for diverse, high-quality text and style variation analysis.

·

Hi @hallisky congrats on this work, really cool!

Would be great to link the models to this paper, see here on how to do that: https://huggingface.co/docs/hub/en/model-cards#linking-a-paper (although I've seen you already link the collection to the paper which is awesome :) ).

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Sign up or log in to comment

Models citing this paper 15

Browse 15 models citing this paper

Datasets citing this paper 3

Spaces citing this paper 1

Collections including this paper 2