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 2410.16458cs.IRcs.AIcs.LG
收藏

STAR:一种利用大语言模型进行推荐的简单免训练方法

STAR: A Simple Training-free Approach for Recommendations using Large Language Models

Information Sciences Institute, University of Southern California(南加州大学信息科学研究所);Google DeepMind(谷歌DeepMind)

Dong-Ho Lee, Adam Kraft, Long Jin, Nikhil Mehta, Taibai Xu, Lichan Hong, Ed H. Chi, Xinyang Yi

AI总结:

本文提出免训练推荐框架 STAR,通过结合 LLM 语义嵌入与协同用户信息进行候选检索,并利用 LLM 成对排序提升下一物品预测,在 Amazon Review 上取得接近或超过最佳监督模型的效果。

摘要:

大语言模型(LLM)的最新进展为推荐系统任务提供了有前景的新方法。尽管当前最先进的方法依赖于对 LLM 进行微调以获得最佳结果,但这一过程成本高昂,并带来显著的工程复杂性。相反,直接使用 LLM 而不进行额外微调的方法会导致推荐质量大幅下降,这通常是因为无法捕捉协同信息。在本文中,我们提出了一种用于推荐的简单免训练方法(Simple Training-free Approach for Recommendation,STAR),这是一个利用 LLM 的框架,无需微调即可应用于各种推荐任务,同时保持高质量的推荐性能。我们的方法包括一个检索阶段,该阶段使用来自 LLM 的语义嵌入并结合协同用户信息来检索候选物品。随后,我们应用 LLM 进行成对排序,以增强下一物品预测。在 Amazon Review 数据集上的实验结果表明,即使仅使用我们的检索阶段,下一物品预测也具有具有竞争力的性能。相对于最佳监督模型,我们的完整方法在 Beauty 上实现了 +23.8% 的 Hits@10 性能提升,在 Toys & Games 上提升 +37.5%,在 Sports & Outdoors 上为 -1.8%。该框架为传统监督模型提供了一种有效的替代方案,凸显了 LLM 在无需大量训练或定制架构的情况下应用于推荐系统的潜力。

英文摘要:

Recent progress in large language models (LLMs) offers promising new approaches for recommendation system tasks. While the current state-of-the-art methods rely on fine-tuning LLMs to achieve optimal results, this process is costly and introduces significant engineering complexities. Conversely, methods that directly use LLMs without additional fine-tuning result in a large drop in recommendation quality, often due to the inability to capture collaborative information. In this paper, we propose a Simple Training-free Approach for Recommendation (STAR), a framework that utilizes LLMs and can be applied to various recommendation tasks without the need for fine-tuning, while maintaining high quality recommendation performance. Our approach involves a retrieval stage that uses semantic embeddings from LLMs combined with collaborative user information to retrieve candidate items. We then apply an LLM for pairwise ranking to enhance next-item prediction. Experimental results on the Amazon Review dataset show competitive performance for next item prediction, even with our retrieval stage alone. Our full method achieves Hits@10 performance of +23.8% on Beauty, +37.5% on Toys & Games, and -1.8% on Sports & Outdoors relative to the best supervised models. This framework offers an effective alternative to traditional supervised models, highlighting the potential of LLMs in recommendation systems without extensive training or custom architectures.

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。

↑