Research on Large Model Empowerment for Recommender Systems

DOI: https://doi.org/10.62517/jiem.202603108

Author(s)

Yan Yang, Sai Wang

Affiliation(s)

Computer School, Central China Normal University, Wuhan, China

Abstract

To address challenges such as data sparsity and cold start issues in traditional recommender systems, this paper explores the application and challenges of large model empowerment in recommender systems. It outlines three primary application directions: optimizing existing algorithms through "pre-training-fine-tuning," transforming recommendation models via conversational interaction and AIGC, and enabling proactive decision-making through agents. It analyzes bottlenecks including computational cost, data privacy, model interpretability, and long-term adaptability. The paper concludes that future progress requires advancing integration through technical optimization, scenario adaptation, and risk management to support personalized recommendation development in the digital economy.

Keywords

Recommender System; Large Language Models; Intelligent Agents

References

[1]WU Y, LU J. Multi Modal Information Generation and Recommendation Driven by Large Models [J]. Journal of Henan Normal University (Natural Science Edition), 2025, 53 (05): 145-151+181. [2]ZHOU X. Research on Efficient Recommendation Algorithm Based on Large Language Model [D]. University of Electronic Science and Technology of China, 2025. [3]LIU P, ZHANG M, WANG P, et al. Algorithm Optimization and Performance Evaluation of Intelligent Knowledge Recommendation System for Convenience Hotline Work Orders Based on Large Models [J]. Digital Technology and Applications, 2025, 43 (03): 16-18. [4]YANG L. Personalized News Recommendation Method Enhanced by Large Language Model [D]. Lanzhou University, 2025. [5]HUANG W, LI Z. Comparative Study of Recommendation Systems under Traditional Mode and Large Language Model [J]. Software Guide, 2025, 24 (02): 204-210. [6]KA Z, ZHAO P, ZHANG B, et al. A Review of Recommendation Systems for Large Language Models [J]. Computer Science, 2024, 51 (S2): 11-21. [7]ZHU M. Research on Personalized Resource Recommendation Method Based on Large Language Model [J]. Journal of Lanzhou University of Arts and Sciences (Natural Science Edition), 2024, 38 (05): 59-64. [8]ZHOU X, DENG X, HUANG W. Large Models and Recommendation Systems Open a New Chapter in Personalized Recommendation [J]. Shanghai Informatization, 2024, (09):35-38. [9]WU G, QIN H, HU Q, et al. Research on Large Language Models and Personalized Recommendations [J]. Journal of Intelligent Systems, 2024, 19 (06): 1351-1365. [10]YE C. Overview of Large Language Model Recommendation Techniques [J]. Electronic Components and Information Technology, 2023, 7 (12): 127-131. [11]WU Z, TANG Y, LIU H. Survey of Personalized Learning Recommendations [J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(1): 21-40. [12]BROWN T, MANN B, RYDER N, et al. Language Models are Few-shot Learners [J]. Advances in Neural Information Processing Systems, 2020, 159: 1877-1901.