超越PII：用户如何尝试估计和缓解隐式LLM推理
Beyond PII: How Users Attempt to Estimate and Mitigate Implicit LLM Inference
AI总结：
研究调查了240名美国参与者对LLM隐式推理风险的估计与缓解策略，发现用户难以预测推理，其重写文本仅在28%的情况下有效，且指出抽象化和增加歧义比改写更有效，强调了LLM交互中推理感知设计的重要性。
摘要：
诸如ChatGPT之类的大型语言模型（LLMs）能够从看似无害的文本中推断出个人属性，这引发了超越记忆数据泄露的隐私风险。尽管先前的研究已经证明了这些风险，但关于用户如何估计和应对却知之甚少。我们对240名美国参与者进行了调查，让他们判断文本片段的推理风险、报告关注程度，并尝试重写以阻止推理。我们将他们的重写文本与ChatGPT和Rescriber（一种最先进的脱敏工具）生成的文本进行了比较。结果显示，参与者在预测推理方面感到困难，表现仅略好于随机猜测。用户重写仅在28%的情况下有效——优于Rescriber，但逊于ChatGPT。我们检查了参与者的重写策略，观察到虽然改写是最常见的策略，但它也是最无效的；相反，抽象化和增加歧义更为成功。我们的工作突显了在LLM交互中推理感知设计的重要性。
英文摘要：
Large Language Models (LLMs) such as ChatGPT can infer personal attributes from seemingly innocuous text, raising privacy risks beyond memorized data leakage. While prior work has demonstrated these risks, little is known about how users estimate and respond. We conducted a survey with 240 U.S. participants who judged text snippets for inference risks, reported concern levels, and attempted rewrites to block inference. We compared their rewrites with those generated by ChatGPT and Rescriber, a state-of-the-art sanitization tool. Results show that participants struggled to anticipate inference, performing a little better than chance. User rewrites were effective in just 28\% of cases - better than Rescriber but worse than ChatGPT. We examined our participants' rewriting strategies, and observed that while paraphrasing was the most common strategy it is also the least effective; instead abstraction and adding ambiguity were more successful. Our work highlights the importance of inference-aware design in LLM interactions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
