控制你所分享的内容：评估语言模型对隐私偏好的遵循程度
Controlling What You Share: Assessing Language Model Adherence to Privacy Preferences
AI总结：
本文提出基于隐私配置文件的本地查询重写框架，并构建多语言数据集 PEEP，使轻量级微调 LLM 在保护敏感信息的同时达到或超过大型零样本模型性能。
摘要：
大型语言模型（LLM）主要通过商业 API 访问，但这通常要求用户将其数据暴露给服务提供商。本文探讨用户如何借助隐私配置文件保持对自身数据的控制：隐私配置文件是用简单自然语言编写的指令，说明哪些内容应当透露、哪些不应透露。我们构建了一个框架，其中本地模型利用这些指令重写查询，在发送给外部模型之前仅隐藏用户认定为敏感的细节，从而在隐私与性能之间取得平衡。为支持该研究，我们推出 PEEP，这是一个多语言数据集，包含经过标注以标出隐私内容的真实用户查询，并与合成隐私配置文件配对。使用轻量级本地 LLM 的实验表明，经过微调后，这些模型不仅显著提升了隐私保护效果，而且性能达到或超过规模大得多的零样本模型。同时，该系统在完全遵循用户指令方面仍面临挑战，这凸显出需要能够更好理解用户定义隐私偏好的模型。
英文摘要：
Large language models (LLMs) are primarily accessed via commercial APIs, but this often requires users to expose their data to service providers. In this paper, we explore how users can stay in control of their data by using privacy profiles: simple natural language instructions that say what should and should not be revealed. We build a framework where a local model uses these instructions to rewrite queries, only hiding details deemed sensitive by the user, before sending them to an external model, thus balancing privacy with performance. To support this research, we introduce PEEP, a multilingual dataset of real user queries annotated to mark private content and paired with synthetic privacy profiles. Experiments with lightweight local LLMs show that, after fine-tuning, they not only achieve markedly better privacy preservation but also match or exceed the performance of much larger zero-shot models. At the same time, the system still faces challenges in fully adhering to user instructions, underscoring the need for models with a better understanding of user-defined privacy preferences.
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。
