SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.15666 · EMNLP · 2024

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

Yejin Choi, Zaid Harchaoui, Ximing Lu, Mitchell Gordon, Skyler Hallinan, Jillian R. Fisher

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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-theart 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 1 . * Co-first authors 1 We release 1) our code at https://github.com/ jfisher52/StyleRemix 2) a demo of STYLEREMIX at https://huggingface.co/spaces/hallisky/ StyleRemix and 3) the datasets (AUTHORMIX and DISC) and trained models in a HuggingFace collection

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2408.15666")
get_code_for_paper("2408.15666")
have("2408.15666")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2408.15666.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2408.15666.svg)](https://syntology.ai/paper/2408.15666)

Connect an agent — have() is free.