arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.19232cs.IRcs.AI
收藏

LLM-RecG:一种面向零样本序列推荐的语义偏置感知框架

LLM-RecG: A Semantic Bias-Aware Framework for Zero-Shot Sequential Recommendation

University of Illinois, Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Yunzhe Li, Junting Wang, Hari Sundaram, Zhining Liu

AI总结:

本文提出语义偏置感知框架LLM-RecG,通过物品级泛化损失和序列级用户行为迁移,提升零样本跨域序列推荐的对齐效果与泛化能力。

摘要:

零样本跨域序列推荐(ZCDSR)能够在无需额外训练或微调的情况下对未见过的领域进行预测,从而解决传统模型在稀疏数据环境中的局限性。近年来,大语言模型(LLMs)的进展通过丰富的预训练表示促进了跨域知识迁移,显著增强了ZCDSR。尽管如此,领域语义偏置——源于领域间词汇和内容重点的差异——仍然是一个持续存在的挑战,导致物品嵌入错位并降低跨域泛化能力。为了解决这一问题,我们提出了一种新颖的语义偏置感知框架,通过在物品级和序列级改进跨域对齐来增强基于LLM的ZCDSR。在物品级,我们引入了一种泛化损失,用于对齐跨领域物品的嵌入(域间紧凑性),同时保留每个物品在其自身领域内的独特特征(域内多样性)。这确保了物品嵌入能够在领域之间有效迁移,而不会退化为过于通用或统一的表示。在序列级,我们开发了一种方法,通过对源域用户序列进行聚类,并在目标域推理过程中应用基于注意力的聚合来迁移用户行为模式。我们动态地将用户嵌入适配到未见过的领域,从而在不需要目标域交互的情况下实现有效的零样本推荐。

英文摘要:

Zero-shot cross-domain sequential recommendation (ZCDSR) enables predictions in unseen domains without additional training or fine-tuning, addressing the limitations of traditional models in sparse data environments. Recent advancements in large language models (LLMs) have significantly enhanced ZCDSR by facilitating cross-domain knowledge transfer through rich, pretrained representations. Despite this progress, domain semantic bias -- arising from differences in vocabulary and content focus between domains -- remains a persistent challenge, leading to misaligned item embeddings and reduced generalization across domains. To address this, we propose a novel semantic bias-aware framework that enhances LLM-based ZCDSR by improving cross-domain alignment at both the item and sequential levels. At the item level, we introduce a generalization loss that aligns the embeddings of items across domains (inter-domain compactness), while preserving the unique characteristics of each item within its own domain (intra-domain diversity). This ensures that item embeddings can be transferred effectively between domains without collapsing into overly generic or uniform representations. At the sequential level, we develop a method to transfer user behavioral patterns by clustering source domain user sequences and applying attention-based aggregation during target domain inference. We dynamically adapt user embeddings to unseen domains, enabling effective zero-shot recommendations without requiring target-domain interactions...

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑