助手抹去了你：AI介导交流中作者身份信号的损失测量
The Assistant Erased You: Measuring Loss of Authorship Signals in AI-Mediated Communication
浏览论文内容
中文总结 AI 辅助
该研究提出方言擦除率（IER），用风格计量模型和LUAR模型发现AI重度重写会削弱个人博客、职场邮件的作者身份信号，还存在双重擦除现象，发布了评估作者身份信号损失的开放协议。
中文摘要 AI 辅助
AI介导交流的研究已探讨AI协助如何塑造人际感知并减少用户间的风格多样性。我们从个体层面提出一个互补问题：消息经AI写作助手重写后，其作者能否仍被与他人区分？我们引入方言擦除率（Idiolect Erasure Rate, IER），定义为AI协助重写后作者身份归因准确率的下降幅度。我们使用风格计量模型和作者身份专属的LUAR模型，在三个生成式AI出现前的语料库上评估IER。重度重写会大幅削弱个人博客和职场邮件中的作者身份信号，使LUAR归因准确率下降多达66.5个百分点，但对主题结构化的新闻影响小得多，因为主题仍是作者身份的预测因素。进一步分析表明，尽管语义重叠度高，重写仍会导致风格趋同；且内容敏感的归因器低估了作者身份专属模型所捕捉的损失。重度重写的消息还可能规避AI文本检测器，使其既难以归因于人类作者，也难以被识别为AI协助生成，我们将这一现象称为双重擦除。IER测量的是计算可归因性而非人类识别，我们将其作为开放且可复现的协议发布，用于评估AI介导交流中的作者身份信号损失。
英文摘要
Research on AI-mediated communication has examined how AI assistance shapes interpersonal perceptions and reduces stylistic diversity across users. We ask a complementary question at the individual level: after a message is rewritten by an AI writing assistant, can its author still be distinguished from others? We introduce the Idiolect Erasure Rate (IER), defined as the reduction in authorship-attribution accuracy following AI-assisted rewriting. We evaluate IER on three pre-generative-AI corpora using a stylometric model and the authorship-specific LUAR model. Heavy rewriting substantially weakens authorship signals in personal blogs and workplace email, reducing LUAR attribution by as much as 66.5 percentage points, but has a much smaller effect on topic-structured news, where topic remains predictive of authorship. Additional analyses suggest that rewriting produces stylistic convergence despite substantial semantic overlap, and that content-sensitive attributers understate the loss captured by authorship-specific models. Heavily rewritten messages may also evade AI-text detectors, making them difficult both to attribute to their human authors and to identify as AI-assisted, a phenomenon we call double erasure. IER measures computational attributability rather than human recognition, and we release it as an open and reproducible protocol for evaluating authorship-signal loss in AI-mediated communication.
