@inproceedings{huang-etal-2025-nap2,
    title = "{NAP}2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human",
    author = "Huang, Shuo  and
      Maclean, William  and
      Kang, Xiaoxi  and
      Xu, Qiongkai  and
      Li, Zhuang  and
      Yuan, Xingliang  and
      Haffari, Gholamreza  and
      Qu, Lizhen",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.476/",
    doi = "10.18653/v1/2025.findings-emnlp.476",
    pages = "8954--8970",
    ISBN = "979-8-89176-335-7",
    abstract = "The widespread use of cloud-based Large Language Models (LLMs) has heightened concerns over user privacy, as sensitive information may be inadvertently exposed during interactions with these services. 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 , 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."
}