arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.26231cs.IR
收藏

ProMax:探索基于分布塑造的LLM衍生资料在推荐系统中的潜力

ProMax: Exploring the Potential of LLM-derived Profiles with Distribution Shaping for Recommender Systems

Anhui University(安徽大学);University of Electronic Science and Technology of China(电子科技大学);The University of Queensland(昆士兰大学)

Yi Zhang, Yiwen Zhang, Kai Zheng, Tong Chen, Hongzhi Yin

AI总结:

本文提出ProMax框架,通过分布塑造技术提升推荐系统性能,利用用户和物品资料的协同关系,改进推荐模型对未见物品的偏好学习。

摘要:

大规模语言模型(LLMs)卓越的文本理解和生成能力重新激活了基于隐式用户反馈的一般推荐领域。而非直接部署LLMs作为推荐模型,更灵活的范式利用其解读用户历史交互和语义上下文的能力,提取结构化资料以表征用户偏好。这些资料可进一步转换为可操作的高维表示,作为增强推荐模型的强大信号。然而,此类资料如何在特征空间中增强推荐性能的机制尚不充分理解。此外,现有研究大多依赖非线性对齐和融合策略来整合这些资料,往往导致语义损失,未能充分挖掘其潜力。为解决这些限制,本文从检索角度重新审视资料,并提出基于分布塑造(ProMax)的简单而有效的推荐框架。我们首先利用密集检索揭示特征空间中用户和物品资料之间的协同关系。基于此见解,我们引入双分布重塑过程,其中资料分布作为引导信号,引导推荐模型学习超出观测交互范围的未见物品偏好。我们将在三个公开数据集上应用ProMax于四种经典推荐方法。结果表明,ProMax显著提升基础模型性能,并优于现有基于LLM的推荐方法。

英文摘要:

The remarkable text understanding and generation capabilities of large language models (LLMs) have revitalized the field of general recommendation based on implicit user feedback. Rather than deploying LLMs directly as recommendation models, a more flexible paradigm leverages their ability to interpret users' historical interactions and semantic contexts to extract structured profiles that characterize user preferences. These profiles can be further transformed into actionable high-dimensional representations, serving as powerful signals to augment and strengthen recommendation models. However, the mechanism by which such profiles enhance recommendation performance within the feature space remains insufficiently understood. Moreover, existing studies predominantly rely on nonlinear alignment and fusion strategies to incorporate these profiles, which often lead to semantic loss and fail to fully exploit their potential. To address these limitations, we revisit profiles from a retrieval perspective and propose a simple yet effective recommendation framework built upon distribution shaping (ProMax) in this paper. We begin by employing dense retrieval to uncover the collaborative relationships between user and item profiles within the feature space. Based on this insight, we introduce a dual distribution-reshaping process, in which the profile distribution acts as a guiding signal to steer the recommendation model toward learning user preferences for unseen items beyond the scope of observed interactions. We apply ProMax to four classic recommendation methods on three public datasets. The results indicate that ProMax substantially improves base model performance and outperforms existing LLM-based recommendation approaches.

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。

↑