让文档搜索在本地完成，保护隐私且性能不降
As We May Search
- 构建本地优先检索框架，模型与索引全在设备端运行
- 100万文档内保持91%以上检索质量，7B模型本地表现接近云端
- 适合重视隐私、需离线处理敏感文件的研究者和用户
个人文档、法律文件和医疗记录中的敏感信息是搜索中最宝贵的资源，但当前检索增强生成系统仍需将内容发送至远程服务器。本文提出本地优先检索（local-first IR）设计哲学，即索引、模型和推理均部署在用户设备上，远程服务仅为可选。本文贡献包括：（1）一个从隐私控制、能力与可访问性三个维度组织检索架构的框架；（2）在消费级硬件上对五个基准进行实验，覆盖1K至100万文档，采用密集检索、BM25及混合融合方法。密集检索在10万文档内保持超过91% nDCG@10，近似HNSW索引将此扩展至百万文档，仅损失2%性能；7B本地语言模型在答案质量上仅比云端基线低4分；（3）基于实证数据呈现支持与反对本地优先检索的多方观点；（4）提出研究议程，识别开放问题。真正的权衡在于可搜索范围而非搜索质量——关键在于能搜什么，而非搜得多好。
原文摘要 · Abstract (English)
The sensitive information in personal documents, legal files, and medical records is among the most valuable things to search, yet current retrieval-augmented generation systems still require sending content to remote servers. We propose local-first IR, a design philosophy where indexes, models, and inference reside on user devices, treating remote services as optional. This paper makes four contributions: (1) a framework organizing retrieval architectures along three dimensions: privacy and control, capability, and accessibility, (2) experiments on consumer hardware across five benchmarks, scaling from 1K to 1M documents with dense retrieval, BM25, and hybrid fusion. Dense retrieval keeps over 91% nDCG@10 up to 100K documents, with approximate HNSW indexes extending this to 1M with only 2% quality loss; a 7B local language model reaches within 4 points of a cloud baseline on answer quality, (3) competing perspectives for and against local-first IR, informed by experimental evidence, and (4) a research agenda identifying open problems. The real tradeoff is scope rather than quality: what matters is what you can search, not how well you can search it.
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。