Recommender Systems with Generative Retrieval

Shashank Rajput, Nikhil Mehta, Anima Singh, Raghunandan H. Keshavan, Trung Vu +8 more
5/8/2023
cs.IRcs.LG

No official code found. Best implementation: EdoardoBotta/RQ-VAE-Recommender (850 stars, MIT, last commit 2026-04-01). 2 more below.

Abstract

Modern recommender systems perform large-scale retrieval by first embedding queries and item candidates in the same unified space, followed by approximate nearest neighbor search to select top candidates given a query embedding. In this paper, we propose a novel generative retrieval approach, where the retrieval model autoregressively decodes the identifiers of the target candidates. To that end, we create semantically meaningful tuple of codewords to serve as a Semantic ID for each item. Given Semantic IDs for items in a user session, a Transformer-based sequence-to-sequence model is trained to predict the Semantic ID of the next item that the user will interact with. To the best of our knowledge, this is the first Semantic ID-based generative model for recommendation tasks. We show that recommender systems trained with the proposed paradigm significantly outperform the current SOTA models on various datasets. In addition, we show that incorporating Semantic IDs into the sequence-to-sequence model enhances its ability to generalize, as evidenced by the improved retrieval performance observed for items with no prior interaction history.

View on arXivView PDF

Code Implementations(3)

XiaoLongtaoo/TIGERCommunity69%
PyTorchMIT

[Pytorch] Unofficial Implementation of "Recommender Systems with Generative Retrieval"

25040Python, Jupyter NotebookJun 17, 202510 months agoMIT
generative-recommendationgenerative-retrievaljupyter-notebookpython3pytorch+4 more
EdoardoBotta/RQ-VAE-RecommenderCommunity65%
MIT

[Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with Generative Retrieval"

850127PythonJun 17, 20246 months agoMIT
generativegenerative-aigenerative-retrievalgumbelrecommendation+11 more
komosam/Generative-RetrievalCommunity61%
Apache-2.0

Minimal implementation of https://arxiv.org/abs/2305.05065

52Python, Jupyter NotebookJun 2, 20251 years agoApache-2.0

Similar Papers

PRISM: Purified Representation and Integrated Semantic Modeling for Generative Sequential Recommendation

84% match2026

Unifying Generative and Dense Retrieval for Sequential Recommendation

83% match1 repo432024

Purely Semantic Indexing for LLM-based Generative Recommendation and Retrieval

83% match1 repo62025

LLaDA-Rec: Discrete Diffusion for Parallel Semantic ID Generation in Generative Recommendation

82% match2025

Variable-Length Semantic IDs for Recommender Systems

82% match1 repo212026

Closing the Performance Gap in Generative Recommenders with Collaborative Tokenization and Efficient Modeling

82% match2025

Cite this paper

@article{rajput2023recommender,
  title  = {Recommender Systems with Generative Retrieval},
  author = {Shashank Rajput and Nikhil Mehta and Anima Singh and Raghunandan H. Keshavan and Trung Vu and Lukasz Heldt and Lichan Hong and Yi Tay and Vinh Q. Tran and Jonah Samost and Maciej Kula and Ed H. Chi and Maheswaran Sathiamoorthy},
  year   = {2023},
  eprint = {2305.05065},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.05065v3},
  journal = {NEURIPS 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.05065.svg)](https://codeofpaper.com/paper/2305.05065)

Discussion