用自然语言指令保护隐私，让大模型只分享用户允许的内容。
Controlling What You Share: Assessing Language Model Adherence to Privacy Preferences
- 用户写指令说明哪些信息不该透露，本地小模型自动改写查询。
- 微调后小模型隐私保护效果显著，性能接近甚至超过大模型。
- 适合关注数据隐私、想自主控制信息泄露的普通用户或开发者。
大型语言模型主要通过商业API访问，但常需向服务提供商暴露用户数据。本文探索通过隐私配置文件——即简单的自然语言指令，明确告知模型哪些内容应隐藏——来让用户掌控数据。我们构建了一个框架：本地模型根据这些指令重写查询，仅在用户认为敏感时隐藏信息，再发送给外部模型，从而在隐私保护与性能间取得平衡。为此，我们提出了PEEP多语言数据集，包含真实用户查询及其标注的隐私内容和合成的隐私配置文件。实验表明，经过微调的轻量级本地LLM不仅显著提升隐私保护能力，其性能还达到甚至超过更大规模的零样本模型。然而，系统仍存在未能完全遵循用户指令的问题，凸显出模型理解用户自定义隐私偏好能力的不足。
原文摘要 · Abstract (English)
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.
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。