Despite the considerable promise of Retrieval-Augmented Generation (RAG), many real-world use cases may create privacy concerns, where the purported utility of RAG-enabled insights comes at the risk of exposing private information to either the LLM or the end user requesting the response. As a potential mitigation, using anonymization techniques to remove personally identifiable information (PII) and other sensitive markers in the underlying data represents a practical and sensible course of action for RAG administrators. Despite a wealth of literature on the topic, no works consider the placement of anonymization along the RAG pipeline, i.e., asking the question, where should anonymization happen? In this case study, we systematically and empirically measure the impact of anonymization at two important points along the RAG pipeline: the dataset and generated answer. We show that differences in privacy-utility trade-offs can be observed depending on where anonymization took place, demonstrating the significance of privacy risk mitigation placement in RAG.

翻译：尽管检索增强生成（RAG）具有显著前景，但许多实际应用场景可能引发隐私问题——RAG功能的预期效用存在风险，即可能向大语言模型或请求响应的终端用户暴露隐私信息。作为一种潜在缓解措施，采用匿名化技术清除底层数据中的个人身份信息（PII）及其他敏感标记，对RAG管理员而言是实用且合理的应对方案。尽管该领域已有大量文献，但尚无研究探讨匿名化在RAG流水线中的部署位置问题，即应当在哪里实施匿名化？在本案例研究中，我们系统性地通过实验测量了RAG流水线中两个关键节点的匿名化效果：数据集层面与生成答案层面。研究表明，依据匿名化实施位置的不同，可以观察到隐私-效用权衡的差异，这验证了RAG中隐私风险缓解策略部署位置的重要性。