Search papers, labs, and topics across Lattice.
The paper introduces GenPOI, a generative framework for Point-of-Interest (POI) retrieval in general map search that uses Large Language Models (LLMs) to address the limitations of semantic matching in underspecified queries. GenPOI unifies heterogeneous search contexts and POIs into structured sequences and uses a novel Geo-Semantic POI Tokenization to encode semantic and geographic context for spatial understanding. Experiments on a large-scale dataset from Tencent Map demonstrate that GenPOI outperforms existing methods by effectively modeling context dependency and search intent reasoning.
LLMs can now directly generate relevant Point-of-Interest (POI) candidates for map search by encoding both semantic and geographic context, outperforming traditional retrieval methods.
Point-of-Interest (POI) retrieval aims to identify relevant candidates from massive-scale POI databases, serving as a cornerstone for diverse location-based services. However, in general map search scenarios, conventional POI retrieval methods are increasingly challenged by underspecified user queries due to their excessive reliance on surface-level semantic matching. Meanwhile, such queries are often highly context-dependent and personalized, yet existing retrieval paradigms struggle to effectively synergize heterogeneous contexts for complex search intent inference. To address these limitations, we revisit general map search from a generative perspective and propose GenPOI, an innovative Generative POI retrieval framework tailored for general search on maps. It seamlessly unifies heterogeneous search contexts and POIs into structured sequences, leveraging the powerful contextual modeling of Large Language Models (LLMs) for spatial-aware candidate generation. Consequently, this generative paradigm effectively solves more challenging queries through profound context dependency modeling and search intent reasoning. Specifically, accounting for the unique geospatial nature of map scenarios, GenPOI introduces a novel Geo-Semantic POI Tokenization to represent each POI as a compact token sequence encoding both semantic and geographic context, thus grounding the LLM's spatial understanding. Additionally, a proximity-aware constrained generation strategy is employed to restrict the decoding space of the LLM, ensuring the validity and geospatial relevance of the generated results. Extensive experiments on large-scale industrial datasets from Tencent Map, comprising POIs at the scale of over 10 million, demonstrate the superior performance of GenPOI.
