EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Turning Cold Entities Warm: LLM-Based User and Item Interaction Simulation for Recommendations

Hao Chen, Lijia Chen, Huan Gong, Kai Xu, Tao Zhu, Haoyan Liu, Feiyu Jiang, Qing Liao, Feiran Huang

ACM Transactions on Information Systems · 30.11.2026 · 44 (8) · 1-28

DOI: 10.1145/3848638 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 13.11.2026. Verfasst von Hao Chen und 8 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Funding Scheme for Research and Innovation of FDCT, NSFC.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recommendation throughout the cold-start period remains a challenge in recommender systems. Strictly cold entities (users/items) have no interactions, while warm-up entities only have a few unreliable interactions. Strict cold-start methods typically overlook warm-up entities, while warm-up methods are generally not designed for entities with no observed interactions. In this article, we propose ProbLLM , an LLM-driven framework that reformulates cold-start recommendation as interaction simulation through a shared retrieve–score–select interface. LLM-based content retrieval first constructs a bounded candidate pool, after which a probability-form prompt elicits a bounded confidence score for every retained pair. Selected interactions retain these confidence scores as soft weights for downstream representation learning. Within this architecture, Filtering Simulation is followed by Refining Simulation for every cold target. Pairwise refinement elicits an LLM confidence score for each filtered candidate before pseudo-interaction selection. A two-phase sequential procedure first initializes the collaborative embeddings on observed interactions and then refines them with confidence-weighted ranking and cold-aware graph aggregation. Across the evaluated settings and matched recommendation backbones, ProbLLM achieves higher performance than the corresponding baselines.

Förderung

  • National Natural Science Foundation of China
  • Funding Scheme for Research and Innovation of FDCT
  • NSFC
  • Innovation Research Foundation of NUDT
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Chen, H., Chen, L., Gong, H., Xu, K., Zhu, T., Liu, H., Jiang, F., Liao, Q., & Huang, F. (2026). Turning Cold Entities Warm: LLM-Based User and Item Interaction Simulation for Recommendations. ACM Transactions on Information Systems, 44(8), 1-28. https://doi.org/10.1145/3848638

Vancouver

Chen H, Chen L, Gong H, Xu K, Zhu T, Liu H, et al. Turning Cold Entities Warm: LLM-Based User and Item Interaction Simulation for Recommendations. ACM Transactions on Information Systems. 2026;44(8):1-28. doi:10.1145/3848638

BibTeX
@article{Chen2026,
  author = {Chen, Hao and Chen, Lijia and Gong, Huan and Xu, Kai and Zhu, Tao and Liu, Haoyan and Jiang, Feiyu and Liao, Qing and Huang, Feiran},
  title = {Turning Cold Entities Warm: LLM-Based User and Item Interaction Simulation for Recommendations},
  journal = {ACM Transactions on Information Systems},
  year = {2026},
  volume = {44},
  number = {8},
  pages = {1--28},
  doi = {10.1145/3848638}
}
Kostenlos starten →