LLMCDSR: Enhancing Cross-Domain Sequential Recommendation with Large Language Models
ACM Transactions on Information Systems · 30.09.2025 · 43 (5) · 1-33
DOI: 10.1145/3715099 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 10.07.2025. Verfasst von Haoran Xin und 3 weiteren Autor:innen. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 107 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key R&D Program of China, Guangzhou-HKUST(GZ) Joint Funding Program.
Abstract (Originalsprache)
Cross-Domain Sequential Recommendation (CDSR) aims to predict users’ preferences based on historical sequential interactions across multiple domains. Existing works focus on the overlapped users who interact in multiple domains to capture the cross-domain correlations. These methods often underperform in practical scenarios featuring both overlapped and non-overlapped users due to the limited cross-domain interactions and knowledge transfer misalignment for non-overlapped users. To address this, we leverage Large Language Models (LLMs) to facilitate CDSR by fully exploiting single-domain interactions. However, LLMs exhibit inherent limitations in handling extensive item repositories and sequential collaborative signals. Moreover, the generation reliability is compromised by the hallucination problem, potentially causing noisy and unstable outputs. To this end, we propose a novel LLMCDSR framework, which employs LLMs to predict unobserved cross-domain interactions, termed pseudo items, within single-domain interactions. Specifically, we first prompt LLMs to execute the Candidate-Free Cross-Domain Interaction Generation task. Then, we devise a Collaborative-Textual Contrastive Pre-Training strategy, learning to infuse collaborative information into textual features. Afterwards, we present a novel Relevance-Aware Meta Recall Network (RMRN) to selectively identify and retrieve high-quality pseudo items from the dataset, where the parameters are optimized in a meta-learning manner. Finally, extensive experiments on two public datasets validate the effectiveness of LLMCDSR in enhancing CDSR. The code and data are available at https://github.com/xhran2010/LLMCDSR .
Förderung
- National Natural Science Foundation of China
- National Key R&D Program of China
- Guangzhou-HKUST(GZ) Joint Funding Program
- Natural Science Foundation of Guangdong Province
Zitieren
APA
Xin, H., Sun, Y., Wang, C., & Xiong, H. (2025). LLMCDSR: Enhancing Cross-Domain Sequential Recommendation with Large Language Models. ACM Transactions on Information Systems, 43(5), 1-33. https://doi.org/10.1145/3715099
Vancouver
Xin H, Sun Y, Wang C, Xiong H. LLMCDSR: Enhancing Cross-Domain Sequential Recommendation with Large Language Models. ACM Transactions on Information Systems. 2025;43(5):1-33. doi:10.1145/3715099
BibTeX
@article{Xin2025,
author = {Xin, Haoran and Sun, Ying and Wang, Chao and Xiong, Hui},
title = {LLMCDSR: Enhancing Cross-Domain Sequential Recommendation with Large Language Models},
journal = {ACM Transactions on Information Systems},
year = {2025},
volume = {43},
number = {5},
pages = {1--33},
doi = {10.1145/3715099}
}
EUVIMED