EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SBT-Rec: A Structured Behavioral Tokenization Framework for LLM-Based Sequential Recommendation

Langgao Cheng, Yanying Mao, Guowang Li, Honghui Chen

Big Data and Cognitive Computing · 10.03.2026 · 10 (3) · 86

DOI: 10.3390/bdcc10030086 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Big Data and Cognitive Computing, online erschienen am 10.03.2026. Verfasst von Langgao Cheng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Generative recommendation systems based on Large Language Models leverage their reasoning capabilities to capture users’ latent interests. However, aligning continuous user behavioral embeddings with the discrete semantic space of LLMs remains a challenge. Direct alignment often leads to semantic mismatch and hallucination issues. Furthermore, existing methods typically rely on multi-stage training strategies to adapt to variations in feature distributions, thereby limiting training efficiency. To address the aforementioned issues, we propose SBT-Rec, a structured behavioral tokenization framework. Specifically, we first design a hierarchical discrete structure discovery module, utilizing a recursive residual quantization mechanism to decompose continuous behavioral vectors into discrete behavioral atoms to resolve modality discrepancies. Second, the multi-scale behavioral semantic reconstruction module reconstructs behavioral representations via residual superposition, thereby reducing data noise. Third, a residual-aware modality distribution aligner is introduced to transform behavioral features into input tokens compatible with the LLM via non-linear mapping. Finally, based on structured discrete representations, we propose a single-stage behavioral-semantic adaptive optimization strategy, achieving end-to-end parameter-efficient fine-tuning. Experiments on the MovieLens, LastFM, and Steam datasets demonstrate that SBT-Rec outperforms existing baseline models in terms of recommendation accuracy, training efficiency, and noise robustness.

Zitieren

APA

Cheng, L., Mao, Y., Li, G., & Chen, H. (2026). SBT-Rec: A Structured Behavioral Tokenization Framework for LLM-Based Sequential Recommendation. Big Data and Cognitive Computing, 10(3), 86. https://doi.org/10.3390/bdcc10030086

Vancouver

Cheng L, Mao Y, Li G, Chen H. SBT-Rec: A Structured Behavioral Tokenization Framework for LLM-Based Sequential Recommendation. Big Data and Cognitive Computing. 2026;10(3):86. doi:10.3390/bdcc10030086

BibTeX
@article{Cheng2026,
  author = {Cheng, Langgao and Mao, Yanying and Li, Guowang and Chen, Honghui},
  title = {SBT-Rec: A Structured Behavioral Tokenization Framework for LLM-Based Sequential Recommendation},
  journal = {Big Data and Cognitive Computing},
  year = {2026},
  volume = {10},
  number = {3},
  pages = {86},
  doi = {10.3390/bdcc10030086}
}
Kostenlos starten →