计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (6A): 240400097-7.doi: 10.11896/jsjkx.240400097

• 大语言模型技术及应用 • 上一篇    下一篇

大语言模型在推荐系统中的应用

李博, 莫先   

  1. 宁夏大学信息工程学院 银川 750021
  • 出版日期:2025-06-16 发布日期:2025-06-12
  • 通讯作者: 莫先(mxian168@nxu.edu.cn)
  • 作者简介:(wjswlb21@163.com)
  • 基金资助:
    国家自然科学基金(62306157);宁夏科技领军人才培养项目(2022GKLRLX03)

Application of Large Language Models in Recommendation System

LI Bo, MO Xian   

  1. College of Information Engineering,Ningxia University,Yinchuan 750021,China
  • Online:2025-06-16 Published:2025-06-12
  • About author:LI Bo,born in 2003,undergraduate,is a member of CCF(No.T9206G).His main research interests include recommend dation algorithm.
    MO Xian,born in 1990,Ph.D,associate professor,master supervisor,is a member of CCF(No.R6178M).His main research interests include data mining,graph neural network,and recommender system.
  • Supported by:
    National Natural Science Foundation of China(62306157) and Science and Technology Leading Talent Training Projects of Ningxia(2022GKLRLX03).

PDF (PC)

42

摘要： 大语言模型(LLMs)在推荐系统(RS)的特征工程与特征编码、预训练与微调和提示学习等阶段发挥着关键作用。通过特征工程与特征编码,LLMs提升了推荐系统的个性化和准确性,同时优化了模型的泛化能力和适应性。研究表明,LLMs在特征工程阶段能够丰富用户画像和提取物品特征;在预训练与微调阶段则通过大量未标记数据训练,为下游任务部署做好准备;在提示学习阶段通过设计有效的指令和提示,提高了模型对推荐任务的理解和解决能力。文中还讨论了LLMs在推荐系统应用中面临的挑战,例如计算成本高、API依赖、数据噪声等问题,研究者正在探索优化策略。未来推荐系统的发展潜力集中在数据增强、微调效率提升、提示设计优化和可解释性增强等方面,这些综合性分析为推荐系统领域的持续发展和创新提供了坚实的理论基础。

关键词: 推荐系统, 大语言模型, 特征工程, 预训练与微调, 提示学习

Abstract: Large language models(LLMs) play a key role in recommendation system(RS),such as feature engineering and feature encoding,pre-training and fine-tuning,and prompt learning.Through feature engineering and feature encoding,LLMs improve the personalization and accuracy of the recommendation system,and optimizes the generalization ability and adaptability of the model.Studies show that LLMs can enrich user profiles and extract item features in the feature engineering stage.The pre-training and fine-tuning phases involve training on a large amount of unlabeled data to prepare for downstream task deployment.The prompt learning phase improves the model’s ability to understand and solve recommendation tasks by designing effective instructions and prompts.This paper also discusses the challenges of LLMs in the application of recommendation systems,such as high computational cost,API dependency,and data noise.Researchers are exploring various optimization strategies.The potential development of recommendation system in the future focuses on data enhancement,fine-tuning efficiency improvement,prompt design optimization,and interpretability enhancement.These comprehensive analyses provide a solid theoretical foundation for the continuous development and innovation in the field of recommendation system.

Key words: Recommendation system, Large language models, Feature engineering, Pre-training and fine-tuning, Prompt learning

中图分类号: 

  • TP183
[1]FAN W,MA Y,LI Q,et al.A graph neural network framework for social recommendations [J].IEEE Transactions on Know-ledge and Data Engineering,2020,34(5):2033-2047.
[2]CHEN X,FAN W,CHEN J,et al.Fairly adaptive negative sampling for recommendations[C]//Proceedings of the ACM Web Conference 2023.2023:3723-3733.
[3]ZHANG S,YAO L,SUN A,et al.Deep learning based recommender system:A survey and new perspectives [J].ACM computing surveys,2019,52(1):1-38.
[4]BROWN T,MANN B,RYDER N,et al.Language models are few-shot learners [J].Advances in neural information processing systems,2020,33:1877-901.
[5]LEE J,TOUTANOVA K J A P A.Pre-training of deep bidirectional transformers for language understanding [J].arXiv:1810.04805,2018,3(8).
[6]LIU C,FAN W,LIU Y,et al.Generative diffusion models on graphs:Methods and applications [J].arXiv:2302.02591,2023.
[7]GAO Y,SHENG T,XIANG Y,et al.Chat-rec:Towards interactive and explainable llms-augmented recommender system [J].arXiv:2303.14524,2023.
[8]CHEN J,MA L,LI X,et al.Knowledge graph completion models are few-shot learners:An empirical study of relation labeling in e-commerce with llms [J].arXiv:2305.09858,2023.
[9]SHAYEGANI E,MAMUN M A A,FU Y,et al.Survey of vulnerabilities in large language models revealed by adversarial attacks [J]. arXiv:2310.10844,2023.
[10]ZHAO H,LIU S,CHANG M,et al.Gimlet:A unified graph-text model for instruction-based molecule zero-shot learning [J].Advances in neural information processing systems,2024,36:5850-5887.
[11]ZHAO H,CHEN H,YANG F,et al.Explainability for large language models:A survey [J].ACM Transactions on Intelligent Systems and Technology,2024,15(2):1-38.
[12]LIU Q,CHEN N,SAKAI T,et al.A first look at llm-powered generative news recommendation [J].CoRR,2023.
[13]GUNARUWAN T,GUNASEKARA W N J N J O M.A Modular Framework for Extensible and Adaptable Recommendation Algorithms [J].NSBM Journal of Management,2007,2(1).
[14]WU C,WU F,QI T,et al.PTUM:Pre-training user model from unlabeled user behaviors via self-supervision [J].arXiv:2010.01494,2020.
[15]GENG S,LIU S,FU Z,et al.Recommendation as language processing(rlp):A unified pretrain,personalized prompt & predict paradigm(p5)[C]//Proceedings of the 16th ACM conference on recommender systems.2022:299-315.
[16]WANG W,LIN X,FENG F,et al.Generative recommendation:Towards next-generation recommender paradigm [J].arXiv:2304.03516,2023.
[17]LUO S,YAO Y,HE B,et al.Integrating large language models into recommendation via mutual augmentation and adaptive aggregation [J].arXiv:2401.13870,2024.
[18]XI Y,LIU W,LIN J,et al.Towards open-world recommendation with knowledge augmentation from large language models[C]//Proceedings of the 18th ACM Conference on Recommender Systems.2024:12-22.
[19]WU J,LIU Q,HU H,et al.Leveraging Large Language Models(LLMs) to Empower Training-Free Dataset Condensation for Content-Based Recommendation [J]. arXiv:2310.09874,2023.
[20]LI Y,MA S,WANG X,et al.Ecomgpt:Instruction-tuning large language models with chain-of-task tasks for e-commerce[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2024,38(17):18582-18590.
[21]LIU Z,CHEN Z,ZHANG M,et al.Modeling User ViewingFlow using Large Language Models for Article Recommendation[C]//Companion Proceedings of the ACM Web Conference 2024.2024:83-92.
[22]GUAN F,KITAYAMA D.Review prediction using large-scale language models for serendipity-oriented tourist spot recommendation and its evaluation[C]//2024 18th International Conference on Ubiquitous Information Management and Communication(IMCOM).IEEE,2024:1-4.
[23]WEI J,WANG X,SCHUURMANS D,et al.Chain-of-thought prompting elicits reasoning in large language models [J].Advances in neural information processing systems,2022,35:24824-24837.
[24]BORISOV V,SEβLER K,LEEMANN T,et al.Language models are realistic tabular data generators [J].arXiv:2210.06280,2022.
[25]DING H,MA Y,DEORAS A,et al.Zero-shot recommender systems [J].arXiv:2105.08318,2021.
[26]HOU Y,HE Z,MCAULEY J,et al.Learning vector-quantizeditem representation for transferable sequential recommenders[C]//Proceedings of the ACM Web Conference 2023.2023:1162-1171.
[27]GONG Y,DING X,SU Y,et al.An unified search and recommendation foundation model for cold-start scenario[C]//Proceedings of the 32nd ACM International Conference on Information and Knowledge Management.2023:4595-4601.
[28]LI P,WANG Y,CHI E H,et al.Prompt tuning large language models on personalized aspect extraction for recommendations [J].arXiv:2306.01475,2023.
[29]RAJPUT S,MEHTA N,SINGH A,et al.Recommender systems with generative retrieval [J].Advances in Neural Information Processing Systems,2024,36:10299-10315.
[30]DEVLIN J,CHANG M W,LEE K,et al.Bert:Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,Volume 1(long and short papers).2019:4171-4186.
[31]CUI Z,MA J,ZHOU C,et al.M6-rec:Generative pretrained language models are open-ended recommender systems [J].arXiv:2205.08084,2022.
[32]FRIEDMAN L,AHUJA S,ALLEN D,et al.Leveraging large language models in conversational recommender systems [J].arXiv:2305.07961,2023.
[33]SHEN T,LI J,BOUADJENEK M R,et al.Towards under-standing and mitigating unintended biases in language model-driven conversational recommendation [J].Information Processing & Management,2023,60(1):103139.
[34]KIM H,JEONG J,KIM K M,et al.Intent-based product collections for e-commerce using pretrained language models[C]//2021 International Conference on Data Mining Workshops(ICDMW).IEEE,2021:228-237.
[35]WANG J,YUAN F,CHENG M,et al.Transrec:Learningtransferable recommendation from mixture-of-modality feedback[C]//Asia-Pacific Web(APWeb) and Web-Age Information Management(WAIM) Joint International Conference on Web and Big Data.Singapore:Springer Nature Singapore,2024:193-208.
[36]LI X L,LIANG P J A P A.Prefix-tuning:Optimizing continuous prompts for generation [J].arXiv:2101.00190,2021.
[37]HU E J,SHEN Y,WALLIS P,et al.Lora:Low-rank adaptation of large language models [J].ICLR,2022,1(2):3.
[38]GAO T,FISCH A,CHEN D J A P A.Making pre-trained language models better few-shot learners [J].arXiv:2012.15723,2020.
[39]DONG Q,LI L,DAI D,et al.A survey on in-context learning [J].arXiv:2301.00234,2022.
[40]WANG X,ZHOU K,WEN J R,et al.Towards unified conversational recommender systems via knowledge-enhanced prompt learning[C]//Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining.2022:1929-1937.
[41]LIU J,LIU C,ZHOU P,et al.Is chatgpt a good recommender? a preliminary study [J].arXiv:2304.10149,2023.
[42]WANG L,ZHANG J,CHEN X,et al.Recagent:A novel simulation paradigm for recommender systems [J].arXiv:2306.02552,2023.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发