AI 中文总结
本文提出基于LLM的CDSR模型DuELRec，通过域门控双专家框架与双采样对比学习缓解跨域序列推荐的负迁移，在10个域的2个数据集上优于26种SOTA方法。
AI 中文摘要
跨域序列推荐（CDSR）基于用户在多个域中的历史交互序列预测用户将交互的下一个物品。近期方法利用在跨域用户序列的文本表示上微调的大语言模型（LLM）来检索推荐物品，这类方法被称为LLMRec。然而，LLMRec主要对物品文本的 token 级自回归模式进行建模，却忽略了物品级协同信号，这种语义错位常导致跨域知识传递出现偏差，即负迁移，从而降低CDSR任务的性能。为解决该问题，本文提出一种新型基于LLM的CDSR模型DuELRec：面向跨域序列推荐的域门控双专家LLM模型。本文提出域门控双专家框架，配备物品感知注意力变换模块，该模块将文本子 token 聚合为物品级表示并实施块级注意力掩码；单域专家将自回归注意力限制在同一域内的物品，跨域专家则允许跨所有域的自回归注意力，门控机制自适应融合二者输出，利用单域信号减少导致负迁移的跨域噪声。其次，本文引入双采样 token-物品对比学习目标，使LLM能从单域和跨域捕获物品级协同信号，该目标通过将 token 级物品文本转换为物品级表示，并从单域和跨域物品池中进行随机负采样以开展对比学习。在两个真实数据集的十个域上开展的大量实验表明，本文模型在推荐性能上优于26种最先进方法。
英文摘要
Cross-Domain Sequential Recommendation (CDSR) predicts the next item a user will interact with based on their historical interaction sequences across multiple domains. Recent approaches leverage Large Language Models (LLMs) finetuned on textual representations of cross-domain user sequences to retrieve the recommended items, referred to as LLMRec. However, LLMRec primarily models the autoregressive patterns of token-level item texts, while overlooking item-level collaborative signals. This semantic misalignment often leads to distorted knowledge transfer across domains-termed negative transfer degrading performance in the CDSR task. To address this issue, we propose a novel LLM-based CDSR model, DuELRec: Domain-Gated Dual Experts with LLMs for Cross-Domain Sequential Recommendation. We propose a domain-gated dual-expert framework, equipped with an item-aware attention transformation module, which aggregates textual subtokens into item-level representations and enforces block-level attention masking. The single-domain expert restricts autoregressive attention to items within the same domain, while the cross-domain expert allows it across all domains. A gating mechanism adaptively fuses their outputs, using single-domain signals to reduce cross-domain noise that causes negative transfer. Second, we introduce a dual-sampling token-to-item contrastive learning objective that allows LLMs to capture the item-level collaborative signals from both single- and cross-domains. This is achieved by transforming token-level item texts into item-level representations and applying stochastic negative sampling from both single- and cross-domain item pools for contrastive learning. Extensive experiments on two real-world datasets across ten domains show that our model outperforms 26 state-of-the-art methods in recommendation performance.
CommentsAccepted at CIKM 2026
