@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2025-nap2">
<titleInfo>
<title>NAP2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuo</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Maclean</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoxi</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiongkai</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingliang</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizhen</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">huang-etal-2025-nap2</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.476/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>8954</start>
<end>8970</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NAP2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human
%A Huang, Shuo
%A Maclean, William
%A Kang, Xiaoxi
%A Xu, Qiongkai
%A Li, Zhuang
%A Yuan, Xingliang
%A Haffari, Gholamreza
%A Qu, Lizhen
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F huang-etal-2025-nap2
%X 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.
%U https://aclanthology.org/2025.findings-emnlp.476/
%P 8954-8970
Markdown (Informal)
[NAP2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human](https://aclanthology.org/2025.findings-emnlp.476/) (Huang et al., Findings 2025)
ACL
- Shuo Huang, William Maclean, Xiaoxi Kang, Qiongkai Xu, Zhuang Li, Xingliang Yuan, Gholamreza Haffari, and Lizhen Qu. 2025. NAP2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 8954–8970, Suzhou, China. Association for Computational Linguistics.