NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human
Lists
Only you see this
Abstract
Increasing concerns about privacy leakage issues in academia and industry arise when employing NLP models from third-party providers to process sensitive texts. To protect privacy before sending sensitive data to those models, we suggest sanitizing sensitive text using two common strategies used by humans: i) deleting sensitive expressions, and ii) obscuring sensitive details by abstracting them. To explore the issues and develop a tool for text rewriting, we curate the first corpus, coined NAP^2, through both crowdsourcing and the use of large language models (LLMs). Compared to the prior works based on differential privacy, which lead to a sharp drop in information utility and unnatural texts, the human-inspired approaches result in more natural rewrites and offer an improved balance between privacy protection and data utility, as demonstrated by our extensive experiments.
BibTeX
@inproceedings{huang2025nap,
author = {Shuo Huang and William MacLean and Xiaoxi Kang and Anqi Wu and Lizhen Qu and Qiongkai Xu and Zhuang Li and Xingliang Yuan and Gholamreza Haffari},
title = {{NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human}},
booktitle = {Conference on Empirical Methods in Natural Language Processing},
year = {2025},
url = {https://openreview.net/forum?id=JIYgcJTBj0},
}