GR-LLMs: Recent Advances in Generative Recommendation Based on Large Language Models

TL;DR

This paper surveys recent progress in generative recommendation systems powered by large language models, highlighting their potential to transform traditional recommendation paradigms through advanced sequence modeling and reasoning capabilities.

Contribution

It provides a comprehensive overview of LLM-based generative recommendation methods, including applications, industrial considerations, and future research directions.

Findings

LLM-based GRs outperform traditional methods in certain tasks

Survey covers application cases and industrial deployment considerations

Identifies promising future research directions in LLM-based GRs

Abstract

In the past year, Generative Recommendations (GRs) have undergone substantial advancements, especially in leveraging the powerful sequence modeling and reasoning capabilities of Large Language Models (LLMs) to enhance overall recommendation performance. LLM-based GRs are forming a new paradigm that is distinctly different from discriminative recommendations, showing strong potential to replace traditional recommendation systems heavily dependent on complex hand-crafted features. In this paper, we provide a comprehensive survey aimed at facilitating further research of LLM-based GRs. Initially, we outline the general preliminaries and application cases of LLM-based GRs. Subsequently, we introduce the main considerations when LLM-based GRs are applied in real industrial scenarios. Finally, we explore promising directions for LLM-based GRs. We hope that this survey contributes to the ongoing advancement of the GR domain.