用自然语言统一处理个人数据，让上下文感知更简单透明
ChainStream: An LLM-based Framework for Unified Synthetic Sensing
- 用自然语言接口统一处理数据，简化上下文感知程序开发
- 在133个任务上实现高效精准的自动感知，准确率显著提升
- 适合想快速构建隐私友好型感知应用的开发者使用
许多应用需要上下文感知以提供个性化和及时服务，但开发感知程序对开发者而言复杂，使用时又存在隐私风险。本文提出利用自然语言作为统一接口来处理个人数据并感知用户上下文，有效降低开发难度并提高数据流程透明度。受大语言模型（LLMs）等生成模型启发，直接应用存在无法应对复杂感知请求、代码生成易出错等问题。为此，我们设计了：1）统一的数据处理框架，使上下文感知程序更简洁；2）反馈引导的查询优化器，提升数据查询信息量。为评估自然语言驱动的上下文感知性能，我们构建了一个包含133个任务的基准测试。大量实验表明，该方法能高效且精确地自动完成上下文感知任务。代码已开源：https://github.com/MobileLLM/ChainStream。
原文摘要 · Abstract (English)
Many applications demand context sensing to offer personalized and timely services. Yet, developing sensing programs can be challenging for developers and using them is privacy-concerning for end-users. In this paper, we propose to use natural language as the unified interface to process personal data and sense user context, which can effectively ease app development and make the data pipeline more transparent. Our work is inspired by large language models (LLMs) and other generative models, while directly applying them does not solve the problem - letting the model directly process the data cannot handle complex sensing requests and letting the model write the data processing program suffers error-prone code generation. We address the problem with 1) a unified data processing framework that makes context-sensing programs simpler and 2) a feedback-guided query optimizer that makes data query more informative. To evaluate the performance of natural language-based context sensing, we create a benchmark that contains 133 context sensing tasks. Extensive evaluation has shown that our approach is able to automatically solve the context-sensing tasks efficiently and precisely. The code is opensourced at https://github.com/MobileLLM/ChainStream.
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。