Large Language Model Enhanced Recommender Systems: Methods, Applications and Trends

Qidong Liu; Xiangyu Zhao; Yuhao Wang; Yejing Wang; Zijian Zhang; Yuqi Sun; Xiang Li; Maolin Wang; Pengyue Jia; Chong Chen; Wei Huang; Feng Tian

doi:10.1145/3711896.3736553

Large Language Model Enhanced Recommender Systems: Methods, Applications and Trends

Qidong Liu
, Xiangyu Zhao^*
, Yuhao Wang
, Yejing Wang
, Zijian Zhang
, Yuqi Sun
, Xiang Li
, Maolin Wang
, Pengyue Jia
, Chong Chen
, Wei Huang
, Feng Tian^*

^*Corresponding author for this work

Xi'an Jiaotong University
City University of Hong Kong
Jilin University
Nanyang Technological University
Tsinghua University
Independent Researcher

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Due to exceptional reasoning and understanding abilities, the Large Language Model (LLM) has revolutionized the pattern of many fields, including recommender systems (RS). There has been a handful of research that focuses on empowering the RS by LLM. Recently, considering the latency and memory costs in real-world applications, LLM-Enhanced RS (LLMERS) is highlighted. This direction pushes the LLM into the online system with a large step by eliminating the utilization of LLM during inference. As a cutting-edge field, there is a clear need for a comprehensive survey to summarize this direction. In this survey, we systematically investigate the most up-to-date works of LLM-enhanced RS to boost this direction. Based on the component of an RS model that the LLM aims to augment, the basic taxonomy includes Knowledge Enhancement, Interaction Enhancement and Model Enhancement. Additionally, we identify several promising research directions. To facilitate access to the surveyed papers, we release a repository.

Original language	English
Title of host publication	KDD 2025 - Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Publisher	Association for Computing Machinery
Pages	6096-6106
Number of pages	11
ISBN (Electronic)	9798400714542
DOIs	https://doi.org/10.1145/3711896.3736553
State	Published - 3 Aug 2025
Externally published	Yes
Event	31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2025 - Toronto, Canada Duration: 3 Aug 2025 → 7 Aug 2025

Publication series

Name	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Volume	2
ISSN (Print)	2154-817X

Conference

Conference	31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2025
Country/Territory	Canada
City	Toronto
Period	3/08/25 → 7/08/25

Keywords

Enhancement
Large Language Model
Recommender Systems

Access to Document

10.1145/3711896.3736553

Cite this

Liu, Q., Zhao, X., Wang, Y., Wang, Y., Zhang, Z., Sun, Y., Li, X., Wang, M., Jia, P., Chen, C., Huang, W., & Tian, F. (2025). Large Language Model Enhanced Recommender Systems: Methods, Applications and Trends. In KDD 2025 - Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 6096-6106). (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; Vol. 2). Association for Computing Machinery . https://doi.org/10.1145/3711896.3736553

Liu, Qidong ; Zhao, Xiangyu ; Wang, Yuhao et al. / Large Language Model Enhanced Recommender Systems : Methods, Applications and Trends. KDD 2025 - Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery , 2025. pp. 6096-6106 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

@inproceedings{f48d5bf4bd2c49618c43acfcc5d826e3,

title = "Large Language Model Enhanced Recommender Systems: Methods, Applications and Trends",

abstract = "Due to exceptional reasoning and understanding abilities, the Large Language Model (LLM) has revolutionized the pattern of many fields, including recommender systems (RS). There has been a handful of research that focuses on empowering the RS by LLM. Recently, considering the latency and memory costs in real-world applications, LLM-Enhanced RS (LLMERS) is highlighted. This direction pushes the LLM into the online system with a large step by eliminating the utilization of LLM during inference. As a cutting-edge field, there is a clear need for a comprehensive survey to summarize this direction. In this survey, we systematically investigate the most up-to-date works of LLM-enhanced RS to boost this direction. Based on the component of an RS model that the LLM aims to augment, the basic taxonomy includes Knowledge Enhancement, Interaction Enhancement and Model Enhancement. Additionally, we identify several promising research directions. To facilitate access to the surveyed papers, we release a repository.",

keywords = "Enhancement, Large Language Model, Recommender Systems",

author = "Qidong Liu and Xiangyu Zhao and Yuhao Wang and Yejing Wang and Zijian Zhang and Yuqi Sun and Xiang Li and Maolin Wang and Pengyue Jia and Chong Chen and Wei Huang and Feng Tian",

note = "Publisher Copyright: {\textcopyright} 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.; 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2025 ; Conference date: 03-08-2025 Through 07-08-2025",

year = "2025",

month = aug,

day = "3",

doi = "10.1145/3711896.3736553",

language = "英语",

series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

publisher = "Association for Computing Machinery ",

pages = "6096--6106",

booktitle = "KDD 2025 - Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining",

address = "美国",

}

Liu, Q, Zhao, X, Wang, Y, Wang, Y, Zhang, Z, Sun, Y, Li, X, Wang, M, Jia, P, Chen, C, Huang, W & Tian, F 2025, Large Language Model Enhanced Recommender Systems: Methods, Applications and Trends. in KDD 2025 - Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, vol. 2, Association for Computing Machinery , pp. 6096-6106, 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2025, Toronto, Canada, 3/08/25. https://doi.org/10.1145/3711896.3736553

Large Language Model Enhanced Recommender Systems: Methods, Applications and Trends. / Liu, Qidong; Zhao, Xiangyu; Wang, Yuhao et al.
KDD 2025 - Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery , 2025. p. 6096-6106 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Large Language Model Enhanced Recommender Systems

T2 - 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2025

AU - Liu, Qidong

AU - Zhao, Xiangyu

AU - Wang, Yuhao

AU - Wang, Yejing

AU - Zhang, Zijian

AU - Sun, Yuqi

AU - Li, Xiang

AU - Wang, Maolin

AU - Jia, Pengyue

AU - Chen, Chong

AU - Huang, Wei

AU - Tian, Feng

PY - 2025/8/3

Y1 - 2025/8/3

N2 - Due to exceptional reasoning and understanding abilities, the Large Language Model (LLM) has revolutionized the pattern of many fields, including recommender systems (RS). There has been a handful of research that focuses on empowering the RS by LLM. Recently, considering the latency and memory costs in real-world applications, LLM-Enhanced RS (LLMERS) is highlighted. This direction pushes the LLM into the online system with a large step by eliminating the utilization of LLM during inference. As a cutting-edge field, there is a clear need for a comprehensive survey to summarize this direction. In this survey, we systematically investigate the most up-to-date works of LLM-enhanced RS to boost this direction. Based on the component of an RS model that the LLM aims to augment, the basic taxonomy includes Knowledge Enhancement, Interaction Enhancement and Model Enhancement. Additionally, we identify several promising research directions. To facilitate access to the surveyed papers, we release a repository.

AB - Due to exceptional reasoning and understanding abilities, the Large Language Model (LLM) has revolutionized the pattern of many fields, including recommender systems (RS). There has been a handful of research that focuses on empowering the RS by LLM. Recently, considering the latency and memory costs in real-world applications, LLM-Enhanced RS (LLMERS) is highlighted. This direction pushes the LLM into the online system with a large step by eliminating the utilization of LLM during inference. As a cutting-edge field, there is a clear need for a comprehensive survey to summarize this direction. In this survey, we systematically investigate the most up-to-date works of LLM-enhanced RS to boost this direction. Based on the component of an RS model that the LLM aims to augment, the basic taxonomy includes Knowledge Enhancement, Interaction Enhancement and Model Enhancement. Additionally, we identify several promising research directions. To facilitate access to the surveyed papers, we release a repository.

KW - Enhancement

KW - Large Language Model

KW - Recommender Systems

UR - https://www.scopus.com/pages/publications/105014313464

U2 - 10.1145/3711896.3736553

DO - 10.1145/3711896.3736553

M3 - 会议稿件

AN - SCOPUS:105014313464

T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SP - 6096

EP - 6106

BT - KDD 2025 - Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining

PB - Association for Computing Machinery

Y2 - 3 August 2025 through 7 August 2025

ER -

Liu Q, Zhao X, Wang Y, Wang Y, Zhang Z, Sun Y et al. Large Language Model Enhanced Recommender Systems: Methods, Applications and Trends. In KDD 2025 - Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery . 2025. p. 6096-6106. (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). doi: 10.1145/3711896.3736553

Large Language Model Enhanced Recommender Systems: Methods, Applications and Trends

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this