LLM-Aligned Geographic Item Tokenization for Local-Life Recommendation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jiang, Hao, Wang, Guoquan, Zhou, Donglin, Yu, Sheng, Zeng, Yang, Zeng, Wencong, Gai, Kun, Zhou, Guorui
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908662107209728
author Jiang, Hao
Wang, Guoquan
Zhou, Donglin
Yu, Sheng
Zeng, Yang
Zeng, Wencong
Gai, Kun
Zhou, Guorui
author_facet Jiang, Hao
Wang, Guoquan
Zhou, Donglin
Yu, Sheng
Zeng, Yang
Zeng, Wencong
Gai, Kun
Zhou, Guorui
contents Recent advances in Large Language Models (LLMs) have enhanced text-based recommendation by enriching traditional ID-based methods with semantic generalization capabilities. Text-based methods typically encode item textual information via prompt design and generate discrete semantic IDs through item tokenization. However, in domain-specific tasks such as local-life services, simply injecting location information into prompts fails to capture fine-grained spatial characteristics and real-world distance awareness among items. To address this, we propose LGSID, an LLM-Aligned Geographic Item Tokenization Framework for Local-life Recommendation. This framework consists of two key components: (1) RL-based Geographic LLM Alignment, and (2) Hierarchical Geographic Item Tokenization. In the RL-based alignment module, we initially train a list-wise reward model to capture real-world spatial relationships among items. We then introduce a novel G-DPO algorithm that uses pre-trained reward model to inject generalized spatial knowledge and collaborative signals into LLMs while preserving their semantic understanding. Furthermore, we propose a hierarchical geographic item tokenization strategy, where primary tokens are derived from discrete spatial and content attributes, and residual tokens are refined using the aligned LLM's geographic representation vectors. Extensive experiments on real-world Kuaishou industry datasets show that LGSID consistently outperforms state-of-the-art discriminative and generative recommendation models. Ablation studies, visualizations, and case studies further validate its effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2511_14221
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-Aligned Geographic Item Tokenization for Local-Life Recommendation
Jiang, Hao
Wang, Guoquan
Zhou, Donglin
Yu, Sheng
Zeng, Yang
Zeng, Wencong
Gai, Kun
Zhou, Guorui
Information Retrieval
Artificial Intelligence
Recent advances in Large Language Models (LLMs) have enhanced text-based recommendation by enriching traditional ID-based methods with semantic generalization capabilities. Text-based methods typically encode item textual information via prompt design and generate discrete semantic IDs through item tokenization. However, in domain-specific tasks such as local-life services, simply injecting location information into prompts fails to capture fine-grained spatial characteristics and real-world distance awareness among items. To address this, we propose LGSID, an LLM-Aligned Geographic Item Tokenization Framework for Local-life Recommendation. This framework consists of two key components: (1) RL-based Geographic LLM Alignment, and (2) Hierarchical Geographic Item Tokenization. In the RL-based alignment module, we initially train a list-wise reward model to capture real-world spatial relationships among items. We then introduce a novel G-DPO algorithm that uses pre-trained reward model to inject generalized spatial knowledge and collaborative signals into LLMs while preserving their semantic understanding. Furthermore, we propose a hierarchical geographic item tokenization strategy, where primary tokens are derived from discrete spatial and content attributes, and residual tokens are refined using the aligned LLM's geographic representation vectors. Extensive experiments on real-world Kuaishou industry datasets show that LGSID consistently outperforms state-of-the-art discriminative and generative recommendation models. Ablation studies, visualizations, and case studies further validate its effectiveness.
title LLM-Aligned Geographic Item Tokenization for Local-Life Recommendation
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2511.14221