Metraipolis › archive › dc_fee890c2d902

HF-SID: High-Fidelity Semantic IDs for Generative Retrieval in Location-Based Services — arXiv:2608.30479

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30479
License (as archived)
CC0-1.0
Archived
2026-10-17T09:44:17.018Z
SHA-256 of the archived text
05d071f60a64642e91ea3470d3054c4584055ff9025456a765da9b0d3e2aa554
Stable URL of this page
https://metraipolis.com/documento/dc_fee890c2d902

How to cite

HF-SID: High-Fidelity Semantic IDs for Generative Retrieval in Location-Based Services — arXiv:2608.30479 — arXiv (en), https://arxiv.org/abs/2608.30479 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fee890c2d902 (Metraipolis archive dc_fee890c2d902, sha256 05d071f60a64642e91ea3470d3054c4584055ff9025456a765da9b0d3e2aa554)
BibTeX
@misc{dcfee890c2d902,
  title = {HF-SID: High-Fidelity Semantic IDs for Generative Retrieval in Location-Based Services — arXiv:2608.30479},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30479},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fee890c2d902; sha256 05d071f60a64642e91ea3470d3054c4584055ff9025456a765da9b0d3e2aa554},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30479. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2608.30479 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T09:12:53.483Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).