paper-with-me

홈 › Papers

Purely Semantic Indexing for LLM-based Generative Recommendation and Retrieval

2025-09-19 · Ruohan Zhang, Jiacheng Li, Julian McAuley, Yupeng Hou arxiv

Semantic identifiers (IDs) have proven effective in adapting large language models for generative recommendation and retrieval. However, existing methods often suffer from semantic ID conflicts, where semantically similar documents (or items) are assigned identical IDs. A common strategy to avoid conflicts is to append a non-semantic token to distinguish them, which introduces randomness and expands the search space, therefore hurting performance. In this paper, we propose purely semantic indexing to generate unique, semantic-preserving IDs without appending non-semantic tokens. We enable unique ID assignment by relaxing the strict nearest-centroid selection and introduce two model-agnostic algorithms: exhaustive candidate matching (ECM) and recursive residual searching (RRS). Extensive experiments on sequential recommendation, product search, and document retrieval tasks demonstrate that our methods improve both overall and cold-start performance, highlighting the effectiveness of ensuring ID uniqueness.

📄 PDF Abstract BibTeX arXiv:2509.16446

Code (0)

등록된 구현이 없습니다.

Tasks

Sequential Recommendation

Similar Papers 제목 키워드 기반

A Simple and Effective Framework for Symmetric Consistent Indexing in Large-Scale Dense Retrieval

2025-12-15 · Huimu Wang, Yiming Qiu, Xingzhi Yao, Zhiguo Chen 외 arxiv

Dense retrieval has become the industry standard in large-scale information retrieval systems due to its high efficiency and competitive accuracy. Its core relies on a coarse-to-fine hierarchical architecture that enable…

Information Retrieval

How to Index Item IDs for Recommendation Foundation Models

2023-05-11 · Wenyue Hua, Shuyuan Xu, Yingqiang Ge, Yongfeng Zhang

Recommendation foundation model utilizes large language models (LLM) for recommendation by converting recommendation tasks into natural language tasks. It enables generative recommendation which directly generates the it…

Language ModelingLanguage Modelling

A Knowledge Graph and Deep Learning-Based Semantic Recommendation Database System for Advertisement Retrieval and Personalization

2025-12-25 · Tangtang Wang, Kaijie Zhang, Kuangcong Liu arxiv

In modern digital marketing, the growing complexity of advertisement data demands intelligent systems capable of understanding semantic relationships among products, audiences, and advertising content. To address this ch…

Bootstrapped Pre-training with Dynamic Identifier Prediction for Generative Retrieval

2024-07-16 · Yubao Tang, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke 외

Generative retrieval uses differentiable search indexes to directly generate relevant document identifiers in response to a query. Recent studies have highlighted the potential of a strong generative retrieval model, tra…

MemorizationRetrieval

LightLM: A Lightweight Deep and Narrow Language Model for Generative Recommendation

2023-10-26 · Kai Mei, Yongfeng Zhang

This paper presents LightLM, a lightweight Transformer-based language model for generative recommendation. While Transformer-based generative modeling has gained importance in various AI sub-fields such as NLP and vision…

HallucinationLanguage ModelingLanguage Modelling