HF-SID：面向基于位置服务中生成式检索的高保真语义ID

中文摘要 AI 辅助

生成式检索在基于位置服务（LBS）中受到越来越多的关注，其中每个兴趣点（POI）都表示为一个语义ID（SID）。由于SID是POI信息传递给生成式模型的唯一通道，因此任何它未能保留的信息在解码时都无法恢复，且LBS检索对现有SID模糊的细粒度差异尤为敏感。具体而言：（1）大语言模型（LLM）对连续坐标的嵌入是不连续的，因此其数值差异无法反映真实地理距离；（2）动态数值属性的尺度差异极大，因此相同的差值对某一属性而言可能是决定性的，而对另一属性而言则可忽略；（3）短文本无法传达层级隶属关系，因为文本相似的POI可能属于不同层级。因此，我们提出HF-SID，它在表示阶段恢复地理、数值和结构保真度，且在任何信息被提交给离散编码之前完成。该方法将坐标转换为连续的3D笛卡尔形式，并将每个数值编码为单个单元，通过具有类型感知嵌入的Geo-CPT和Num-CPT在大语言模型中进行整合；仅应用于最后一层残差的基于结构的对比学习目标，可将共享粗标签但细粒度不同的同位置POI区分开来。由于这些机制丰富了表示而非延长标识符，HF-SID使用3个token的SID，且无额外解码成本。在一个大规模工业级数据集上的实验表明，HF-SID能有效提升LBS生成式检索的细粒度区分能力。

英文摘要

Generative retrieval has attracted increasing attention in Location-Based Services (LBS), where each Point-of-Interest (POI) is represented as a Semantic ID (SID). As the SID is the only channel through which POI information reaches the generative model, whatever it fails to preserve is irrecoverable at decoding time, and LBS retrieval is especially sensitive to the fine-grained differences that existing SIDs blur. Specifically, (1) LLMs embed continuous coordinates discontinuously, so their numeric differences do not reflect true geographic distance; (2) dynamic numerical attributes differ vastly in scale, so an identical gap may be decisive for one attribute yet negligible for another; and (3) short text cannot convey hierarchical affiliation, as text-similar POIs may belong to different hierarchies. We therefore propose HF-SID, which restores geographic, numerical, and structural fidelity at the representation stage, before any information is committed to a discrete code. It transforms coordinates into a continuous 3D Cartesian form and encodes each numerical value as a single unit, consolidated inside the LLM by Geo-CPT and Num-CPT with type-aware embeddings; a Structure-based Contrastive Learning objective, applied only to the last-layer residual, then separates co-located POIs that share a coarse tag but differ at the fine level. Because these mechanisms enrich the representation rather than lengthen the identifier, HF-SID uses a 3-token SID at no extra decoding cost. On a large-scale industrial

发表机构

• AMAP, Alibaba Group（高德，阿里巴巴集团）
• University of Science and Technology of China（中国科学技术大学）
• Tsinghua University（清华大学）

机构由 AI 辅助整理，请以论文原文为准。