用大模型实现自然语言的多地点联合搜索，提升地图查询体验。
SEQ-GPT: LLM-assisted Spatial Query via Example
- 通过大模型理解自然语言，实现基于示例的多地点联合搜索。
- 支持用户交互澄清与动态调整，搜索过程更灵活智能。
- 适合需要复杂空间查询的导航、城市规划等场景使用者。
当前在线地图等空间服务主要依赖用户输入查询进行位置搜索，但在执行复杂任务（如同时查找多个地点）时用户体验受限。本文研究扩展场景——空间示例查询（Spatial Exemplar Query, SEQ），即用户通过指定示例联合搜索多个相关位置。我们提出SEQ-GPT，一个基于大语言模型（LLM）的空间查询系统，支持以自然语言进行更灵活的SEQ搜索。利用LLM的语言能力，系统可在查询过程中实现用户交互澄清与动态调整，提升搜索准确性。我们还设计了定制化的LLM适配流程，通过对话合成与多模态协作，实现自然语言与结构化空间数据及查询的对齐。该系统在真实数据与应用场景下实现了端到端演示，为拓展空间搜索能力提供了新范式。
原文摘要 · Abstract (English)
Contemporary spatial services such as online maps predominantly rely on user queries for location searches. However, the user experience is limited when performing complex tasks, such as searching for a group of locations simultaneously. In this study, we examine the extended scenario known as Spatial Exemplar Query (SEQ), where multiple relevant locations are jointly searched based on user-specified examples. We introduce SEQ-GPT, a spatial query system powered by Large Language Models (LLMs) towards more versatile SEQ search using natural language. The language capabilities of LLMs enable unique interactive operations in the SEQ process, including asking users to clarify query details and dynamically adjusting the search based on user feedback. We also propose a tailored LLM adaptation pipeline that aligns natural language with structured spatial data and queries through dialogue synthesis and multi-model cooperation. SEQ-GPT offers an end-to-end demonstration for broadening spatial search with realistic data and application scenarios.
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。