EUVIMEDEUVIMED entdecken
Crossref

LLM Collaborative Filtering: User-Item Graph as New Language

Huachi Zhou, Yujing Zhang, Hao Chen, Qinggang Zhang, Qijie Shen, Feiran Huang, Xiao Huang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (41) · 35103-35111

DOI: 10.1609/aaai.v40i41.40816 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Huachi Zhou und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In collaborative filtering, learning effective embeddings for users and items from interaction data remains a central challenge. While recent efforts leverage large language models (LLMs) to enhance collaborative filtering, two critical limitations persist: (1) Efficiency: LLM-based inference is significantly slower than traditional embedding-based search; and (2) Topological Modeling: LLMs struggle to capture graph structures, which are essential for modeling multi-order user-item interactions. To address these limitations, we propose New Language Collaborative Filtering (NLCF), a framework that aligns LLMs with collaborative filtering by conceptualizing user-item graphs as new languages. This approach is based on two key insights: (1) LLMs excel at mastering new languages when trained on suitable corpora, and (2) the empirical conditional probability between tokens in corpora converges to the transition probabilities between nodes in graphs. NLCF translates user-item graphs into corpora, where users and items are treated as tokens. These corpora are used to fine-tune LLMs, and the learned representations are aggregated to construct user and item embeddings that encode multi-order interactions. Unlike methods that deploy LLMs for inference, NLCF distills LLM knowledge learned from corpora into compact embeddings, enabling both efficient training and real-time inference. The framework has been deployed on a billion-scale e-commerce platform for several months. Extensive experiments demonstrate that NLCF outperforms traditional graph CF models and LLM-based baselines while achieving significant training and inference efficiency improvement over LLM-based baselines.

Zitieren

APA

Zhou, H., Zhang, Y., Chen, H., Zhang, Q., Shen, Q., Huang, F., & Huang, X. (2026). LLM Collaborative Filtering: User-Item Graph as New Language. Proceedings of the AAAI Conference on Artificial Intelligence, 40(41), 35103-35111. https://doi.org/10.1609/aaai.v40i41.40816

Vancouver

Zhou H, Zhang Y, Chen H, Zhang Q, Shen Q, Huang F, et al. LLM Collaborative Filtering: User-Item Graph as New Language. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(41):35103-35111. doi:10.1609/aaai.v40i41.40816

BibTeX
@article{Zhou2026,
  author = {Zhou, Huachi and Zhang, Yujing and Chen, Hao and Zhang, Qinggang and Shen, Qijie and Huang, Feiran and Huang, Xiao},
  title = {LLM Collaborative Filtering: User-Item Graph as New Language},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {41},
  pages = {35103--35111},
  doi = {10.1609/aaai.v40i41.40816}
}
Kostenlos starten →