Retrieval Augmented Generation (RAG) systems deployed across organizational boundaries face fundamental tensions between security, accuracy, and efficiency. Current encryption methods expose plaintext during decryption, while federated architectures prevent resource integration and incur substantial overhead. We introduce Trans-RAG, implementing a novel vector space language paradigm where each organization's knowledge exists in a mathematically isolated semantic space. At the core lies vector2Trans, a multi-stage transformation technique that enables queries to dynamically "speak" each organization's vector space "language" through query-centric transformations, eliminating decryption overhead while maintaining native retrieval efficiency. Security evaluations demonstrate near-orthogonal vector spaces with 89.90° angular separation and 99.81% isolation rates. Experiments across 8 retrievers, 3 datasets, and 3 LLMs show minimal accuracy degradation (3.5% decrease in nDCG@10) and significant efficiency improvements over homomorphic encryption.

翻译：跨组织边界部署的检索增强生成（RAG）系统在安全性、准确性与效率之间面临根本性矛盾。现有加密方法在解密过程中暴露明文，而联邦架构既阻碍资源整合又引入大量开销。我们提出Trans-RAG，实现了一种新型向量空间语言范式，使各组织的知识存在于数学上隔离的语义空间中。其核心是向量到向量变换（vector2Trans）这一多阶段变换技术，通过面向查询的变换使查询能够动态"理解"各组织向量空间的"语言"，在消除解密开销的同时保持原生检索效率。安全性评估显示，该方法实现了近正交的向量空间（89.90°夹角分离度，99.81%隔离率）。在8种检索器、3个数据集和3种大语言模型上的实验表明，与同态加密相比，该方法准确率损失极小（nDCG@10下降3.5%），效率提升显著。