SETRec++: Scaling Order-agnostic Identifier for Large Language Model-based Generative Recommendation
ACM Transactions on Recommender Systems · 10.08.2026
DOI: 10.1145/3838805 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Recommender Systems, online erschienen am 10.08.2026. Verfasst von Xinyu Lin und 8 weiteren Autor:innen. Die Arbeit nennt 69 Literaturangaben.
Abstract (Originalsprache)
Leveraging Large Language Models (LLMs) for generative recommendation has attracted significant research interest, where item tokenization is a critical step. It involves assigning item identifiers for LLMs to encode user history and generate the next item. Existing approaches leverage either token-sequence identifiers, representing items as discrete token sequences, or single-token identifiers, using ID or semantic embeddings. Token-sequence identifiers face issues such as the local optima problem in beam search and low generation efficiency due to step-by-step generation. In contrast, single-token identifiers fail to capture rich semantics or encode Collaborative Filtering (CF) information, resulting in suboptimal performance. To address these issues, we propose three fundamental principles for item identifier design: 1) integrating both CF and semantic information to fully capture multi-dimensional item information, 2) designing order-agnostic identifiers without token dependency, mitigating the local optima issue and achieving simultaneous generation for generation efficiency, and 3) disentangling semantics across different tokens, unlocking the potential of scaling order-agnostic identifier. Accordingly, we introduce a novel set identifier paradigm, representing each item as a set of order-agnostic tokens. To implement, we propose SETRec, which leverages CF and semantic tokenizers to obtain order-agnostic multi-dimensional tokens. To eliminate token dependency, SETRec uses a sparse attention mask for user history encoding and a query-guided generation mechanism for simultaneous token generation. We instantiate SETRec on T5 and Qwen (from 1.5B to 7B). To reinforce disentanglement between tokens, we propose SETRec++, which introduces two disentanglement strategies, i.e., disentangled regularization loss and token masking mechanism. Experiments on four datasets demonstrate its effectiveness across various scenarios ( e.g., full ranking, warm- and cold-start ranking, and various item popularity groups). Moreover, results validate SETRec’s superior efficiency and scalability on cold-start items as model sizes increase, and SETRec++’s potential in the scalability of order-agnostic identifier.
Zitieren
APA
Lin, X., Zhang, C., Liu, Y., Shi, H., Wang, W., Feng, F., Wang, Q., Ng, S., & Chua, T. (2026). SETRec++: Scaling Order-agnostic Identifier for Large Language Model-based Generative Recommendation. ACM Transactions on Recommender Systems. https://doi.org/10.1145/3838805
Vancouver
Lin X, Zhang C, Liu Y, Shi H, Wang W, Feng F, et al. SETRec++: Scaling Order-agnostic Identifier for Large Language Model-based Generative Recommendation. ACM Transactions on Recommender Systems. 2026. doi:10.1145/3838805
BibTeX
@article{Lin2026,
author = {Lin, Xinyu and Zhang, Chuanyu and Liu, Yufan and Shi, Haihan and Wang, Wenjie and Feng, Fuli and Wang, Qifan and Ng, See-Kiong and Chua, Tat-Seng},
title = {SETRec++: Scaling Order-agnostic Identifier for Large Language Model-based Generative Recommendation},
journal = {ACM Transactions on Recommender Systems},
year = {2026},
doi = {10.1145/3838805}
}
EUVIMED