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 2402.13840cs.IRcs.AI
收藏

基于大语言模型的多视角意图学习与对齐的会话式推荐

Multi-view Intent Learning and Alignment with Large Language Models for Session-based Recommendation

School of Big Data and Software Engineering, Chongqing University(重庆大学大数据与软件学院);BNRist, Tsinghua University(清华大学BNRist);Tencent Inc.(腾讯公司)

Shutong Qiao, Wei Zhou, Junhao Wen, Chen Gao, Qun Luo, Peixuan Chen, Yong Li

AI总结:

针对会话式推荐(SBR)中数据稀疏、LLM应用受限等问题,提出两阶段LLM增强框架,通过多视角意图学习与对齐融合语义和行为信号,在真实数据集上提升性能并发布代码。

摘要:

会话式推荐(SBR)方法通常依赖用户行为数据,但会受会话数据稀疏性的影响,限制性能。研究人员发现,除行为信号外,物品描述中的丰富语义信息对捕捉隐藏用户意图至关重要。尽管大语言模型(LLMs)为利用这类语义数据提供了新途径,但会话匿名性、短序列特性及LLM训练成本高的挑战,阻碍了轻量高效的SBR LLM框架的发展。为解决上述挑战,我们提出一种LLM增强的SBR框架,整合多视角的语义与行为信号。该两阶段框架既利用LLM和传统SBR模型的优势,又最小化训练成本。第一阶段,我们使用多视角提示在会话语义层面推断潜在用户意图,并通过意图定位模块缓解LLM幻觉;第二阶段,我们将这些语义推断与行为表示对齐并统一,有效融合大模型与小模型的见解。在两个真实数据集上的大量实验表明,LLM4SBR框架能有效提升模型性能。我们在https://github.com/tsinghua-fib-lab/LLM4SBR发布了代码及基线模型。

英文摘要:

Session-based recommendation (SBR) methods often rely on user behavior data, which can struggle with the sparsity of session data, limiting performance. Researchers have identified that beyond behavioral signals, rich semantic information in item descriptions is crucial for capturing hidden user intent. While large language models (LLMs) offer new ways to leverage this semantic data, the challenges of session anonymity, short-sequence nature, and high LLM training costs have hindered the development of a lightweight, efficient LLM framework for SBR. To address the above challenges, we propose an LLM-enhanced SBR framework that integrates semantic and behavioral signals from multiple views. This two-stage framework leverages the strengths of both LLMs and traditional SBR models while minimizing training costs. In the first stage, we use multi-view prompts to infer latent user intentions at the session semantic level, supported by an intent localization module to alleviate LLM hallucinations. In the second stage, we align and unify these semantic inferences with behavioral representations, effectively merging insights from both large and small models. Extensive experiments on two real datasets demonstrate that the LLM4SBR framework can effectively improve model performance. We release our codes along with the baselines at https://github.com/tsinghua-fib-lab/LLM4SBR.

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。

↑