SEQ-GPT: LLM-assisted Spatial Query via Example

TL;DR

SEQ-GPT leverages Large Language Models to enhance complex spatial searches by enabling natural language interactions, clarifications, and dynamic adjustments, thereby improving user experience in spatial query tasks.

Contribution

The paper introduces SEQ-GPT, a novel LLM-powered system that facilitates versatile spatial exemplar queries through natural language and interactive operations.

Findings

Demonstrates effective LLM integration for spatial queries

Enables interactive clarification and dynamic search adjustments

Broadens spatial search capabilities with realistic data

Abstract

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.