用大模型个性化改写文本，隐藏作者身份
Personalized Author Obfuscation with Large Language Models
- 针对每位作者定制提示词，提升风格混淆效果
- 模型整体有效，但不同作者表现差异明显呈双峰分布
- 适合隐私保护、匿名投稿等需要隐藏作者的场景
本文研究大语言模型在通过改写和改变写作风格来隐藏作者身份方面的有效性。不同于全局评估模型性能的方法，我们关注个体作者层面的表现，分析不同作者的混淆效果差异。结果显示，尽管大模型总体有效，但其效果呈现双峰分布，个体间差异显著。为此，我们提出一种个性化提示方法，相比标准提示技术表现更优，部分缓解了效果不均的问题。
原文摘要 · Abstract (English)
In this paper, we investigate the efficacy of large language models (LLMs) in obfuscating authorship by paraphrasing and altering writing styles. Rather than adopting a holistic approach that evaluates performance across the entire dataset, we focus on user-wise performance to analyze how obfuscation effectiveness varies across individual authors. While LLMs are generally effective, we observe a bimodal distribution of efficacy, with performance varying significantly across users. To address this, we propose a personalized prompting method that outperforms standard prompting techniques and partially mitigates the bimodality issue.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。