Large Language Models Augmented Rating Prediction in Recommender System

Sichun Luo; Jiansheng Wang; Aojun Zhou; Li Ma; Linqi Song

doi:10.1109/ICASSP48485.2024.10447514

Large Language Models Augmented Rating Prediction in Recommender System

Sichun Luo
, Jiansheng Wang
, Aojun Zhou
, Li Ma
, Linqi Song^*

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

16 Citations (Scopus)

Abstract

Recently, large language models (LLMs) have demonstrated impressive capabilities and gained widespread applications. However, their direct application to recommendation tasks (e.g., rating prediction task) often falls short of optimal results due to a lack of understanding of collaborative information in recommendations. In this paper, we propose Large lAnguage Model Augmented Recommendation (LAMAR) framework to address this limitation. Instead of relying solely on LLMs, our framework combines their outputs with traditional recommendation models, leveraging both collaborative and semantic information. We further enhance the recommendation performance through an ensemble of diverse prompts and utilize LLMs to extract side information for augmenting traditional recommendation models. Empirical studies on realworld datasets demonstrate that LAMAR outperforms existing approaches, highlighting the benefits of leveraging LLMs in recommendation systems. Code is available at https: //github.com/sichunluo/LAMAR. ©2024 IEEE.

Original language	English
Title of host publication	2024 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings
Publisher	IEEE
Pages	7960-7964
ISBN (Electronic)	979-8-3503-4485-1
ISBN (Print)	979-8-3503-4486-8
DOIs	https://doi.org/10.1109/ICASSP48485.2024.10447514
Publication status	Published - 2024
Event	49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024) - COEX, Seoul, Korea, Republic of Duration: 14 Apr 2024 → 19 Apr 2024 https://2024.ieeeicassp.org/

Publication series

Name	Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing
ISSN (Print)	1520-6149
ISSN (Electronic)	2379-190X

Conference

Conference	49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)
Place	Korea, Republic of
City	Seoul
Period	14/04/24 → 19/04/24
Internet address	https://2024.ieeeicassp.org/

Funding

This work was supported in part by the National Natural Science Foundation of China under Grant 62371411, the Research Grants Council of the Hong Kong SAR under Grant GRF 11217823, InnoHK initiative, the Government of the HKSAR, Laboratory for AI-Powered Financial Technologies.

Research Keywords

recommender system
large language model
rating prediction

RGC Funding Information

RGC-funded

Access Output

10.1109/ICASSP48485.2024.10447514

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

GRF: Towards Building An Adaptive Distributed Computation Framework for Massive Context Interplay
SONG, L. (Principal Investigator / Project Coordinator) & LAN, T. (Co-Investigator)
1/01/24 → …
Project: Research

Cite this

Luo, S., Wang, J., Zhou, A., Ma, L., & Song, L. (2024). Large Language Models Augmented Rating Prediction in Recommender System. In 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings (pp. 7960-7964). (Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing). IEEE. https://doi.org/10.1109/ICASSP48485.2024.10447514

@inproceedings{12cb2ecfaa04427fbd8bba441f4855ca,

title = "Large Language Models Augmented Rating Prediction in Recommender System",

abstract = "Recently, large language models (LLMs) have demonstrated impressive capabilities and gained widespread applications. However, their direct application to recommendation tasks (e.g., rating prediction task) often falls short of optimal results due to a lack of understanding of collaborative information in recommendations. In this paper, we propose Large lAnguage Model Augmented Recommendation (LAMAR) framework to address this limitation. Instead of relying solely on LLMs, our framework combines their outputs with traditional recommendation models, leveraging both collaborative and semantic information. We further enhance the recommendation performance through an ensemble of diverse prompts and utilize LLMs to extract side information for augmenting traditional recommendation models. Empirical studies on realworld datasets demonstrate that LAMAR outperforms existing approaches, highlighting the benefits of leveraging LLMs in recommendation systems. Code is available at https: //github.com/sichunluo/LAMAR. {\textcopyright}2024 IEEE.",

keywords = "recommender system, large language model, rating prediction",

author = "Sichun Luo and Jiansheng Wang and Aojun Zhou and Li Ma and Linqi Song",

year = "2024",

doi = "10.1109/ICASSP48485.2024.10447514",

language = "English",

isbn = "979-8-3503-4486-8",

series = "Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing",

publisher = "IEEE",

pages = "7960--7964",

booktitle = "2024 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings",

address = "United States",

note = "49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024) ; Conference date: 14-04-2024 Through 19-04-2024",

url = "https://2024.ieeeicassp.org/",

}

Luo, S, Wang, J, Zhou, A, Ma, L & Song, L 2024, Large Language Models Augmented Rating Prediction in Recommender System. in 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, pp. 7960-7964, 49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024), Seoul, Korea, Republic of, 14/04/24. https://doi.org/10.1109/ICASSP48485.2024.10447514

Large Language Models Augmented Rating Prediction in Recommender System. / Luo, Sichun; Wang, Jiansheng; Zhou, Aojun et al.
2024 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings. IEEE, 2024. p. 7960-7964 (Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Large Language Models Augmented Rating Prediction in Recommender System

AU - Luo, Sichun

AU - Wang, Jiansheng

AU - Zhou, Aojun

AU - Ma, Li

AU - Song, Linqi

PY - 2024

Y1 - 2024

N2 - Recently, large language models (LLMs) have demonstrated impressive capabilities and gained widespread applications. However, their direct application to recommendation tasks (e.g., rating prediction task) often falls short of optimal results due to a lack of understanding of collaborative information in recommendations. In this paper, we propose Large lAnguage Model Augmented Recommendation (LAMAR) framework to address this limitation. Instead of relying solely on LLMs, our framework combines their outputs with traditional recommendation models, leveraging both collaborative and semantic information. We further enhance the recommendation performance through an ensemble of diverse prompts and utilize LLMs to extract side information for augmenting traditional recommendation models. Empirical studies on realworld datasets demonstrate that LAMAR outperforms existing approaches, highlighting the benefits of leveraging LLMs in recommendation systems. Code is available at https: //github.com/sichunluo/LAMAR. ©2024 IEEE.

AB - Recently, large language models (LLMs) have demonstrated impressive capabilities and gained widespread applications. However, their direct application to recommendation tasks (e.g., rating prediction task) often falls short of optimal results due to a lack of understanding of collaborative information in recommendations. In this paper, we propose Large lAnguage Model Augmented Recommendation (LAMAR) framework to address this limitation. Instead of relying solely on LLMs, our framework combines their outputs with traditional recommendation models, leveraging both collaborative and semantic information. We further enhance the recommendation performance through an ensemble of diverse prompts and utilize LLMs to extract side information for augmenting traditional recommendation models. Empirical studies on realworld datasets demonstrate that LAMAR outperforms existing approaches, highlighting the benefits of leveraging LLMs in recommendation systems. Code is available at https: //github.com/sichunluo/LAMAR. ©2024 IEEE.

KW - recommender system

KW - large language model

KW - rating prediction

U2 - 10.1109/ICASSP48485.2024.10447514

DO - 10.1109/ICASSP48485.2024.10447514

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 979-8-3503-4486-8

T3 - Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing

SP - 7960

EP - 7964

BT - 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings

PB - IEEE

T2 - 49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)

Y2 - 14 April 2024 through 19 April 2024

ER -

Luo S, Wang J, Zhou A, Ma L, Song L. Large Language Models Augmented Rating Prediction in Recommender System. In 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings. IEEE. 2024. p. 7960-7964. (Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing). Epub 2024 Mar 18. doi: 10.1109/ICASSP48485.2024.10447514

Large Language Models Augmented Rating Prediction in Recommender System

Abstract

Publication series

Conference

Funding

Research Keywords

RGC Funding Information

Access Output

Other Access Options

Permanent Link

Fingerprint

Projects

GRF: Towards Building An Adaptive Distributed Computation Framework for Massive Context Interplay

Cite this