SEQ-GPT: LLM-assisted Spatial Query via Example

2025-08-14

AI Summary

Existing spatial services rely on single-point queries, making them inadequate for complex tasks requiring synchronous retrieval of multiple related locations. To address this, we propose Spatial Exemplar Query (SEQ), a novel paradigm wherein users specify multiple representative location examples to drive joint spatial search. We design SEQ-GPT—a LLM-based system integrating dialogue synthesis, multimodal coordination, and a customized adaptation pipeline—to achieve precise alignment from natural language to structured spatial queries. The system further supports interactive clarification and feedback-driven dynamic optimization. End-to-end experiments on real-world datasets and application scenarios demonstrate that SEQ-GPT significantly improves accuracy, interpretability, and user experience for multi-exemplar joint retrieval, while exhibiting strong generalization capability across diverse spatial tasks.

Technology Category

• Search and Optimization: Learning to Search
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• Enhancing spatial queries using natural language via LLMs
• Addressing complex multi-location search limitations in maps
• Bridging natural language and structured spatial data processing

Innovation

• LLM-powered spatial query system
• Natural language for versatile search
• Dialogue synthesis for data alignment