SEQ-GPT: LLM-assisted Spatial Query via Example
This work addresses a domain-specific problem for users of spatial services like online maps, offering an incremental improvement by integrating LLMs into existing query systems.
The paper tackles the problem of complex spatial searches, such as finding multiple locations simultaneously, by introducing SEQ-GPT, an LLM-assisted system that uses natural language for Spatial Exemplar Query, enabling interactive operations like query clarification and dynamic adjustments based on user feedback.
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.