Large language models (LLMs), exemplified by OpenAI ChatGPT and Google Bard, have transformed the way we interact with cyber technologies. In this paper, we study the possibility of connecting LLM with wireless sensor networks (WSN). A successful design will not only extend LLM's knowledge landscape to the physical world but also revolutionize human interaction with WSN. To the end, we present ChatTracer, an LLM-powered real-time Bluetooth device tracking system. ChatTracer comprises three key components: an array of Bluetooth sniffing nodes, a database, and a fine-tuned LLM. ChatTracer was designed based on our experimental observation that commercial Apple/Android devices always broadcast hundreds of BLE packets per minute even in their idle status. Its novelties lie in two aspects: i) a reliable and efficient BLE packet grouping algorithm; and ii) an LLM fine-tuning strategy that combines both supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF). We have built a prototype of ChatTracer with four sniffing nodes. Experimental results show that ChatTracer not only outperforms existing localization approaches, but also provides an intelligent interface for user interaction.

翻译：大语言模型（LLMs），如OpenAI ChatGPT和Google Bard，已彻底改变了我们与网络技术的交互方式。本文研究将LLM与无线传感器网络（WSN）连接的可能性。若设计成功，不仅能将LLM的知识图谱拓展至物理世界，还将彻底革新人类与WSN的交互方式。为此，我们提出ChatTracer——一个由大语言模型驱动的实时蓝牙设备追踪系统。ChatTracer包含三个核心组件：蓝牙嗅探节点阵列、数据库及经过微调的LLM。基于实验观察（即使处于空闲状态，商用苹果/安卓设备每分钟也会广播数百个BLE数据包），我们设计了ChatTracer。其创新性体现在两个方面：i）可靠高效的BLE数据包分组算法；ii）结合监督式微调（SFT）与基于人类反馈的强化学习（RLHF）的LLM微调策略。我们搭建了包含四个嗅探节点的ChatTracer原型系统。实验结果表明，ChatTracer不仅优于现有定位方法，还提供了智能化的用户交互界面。