With the rapid development of online services, recommender systems (RS) have become increasingly indispensable for mitigating information overload. Despite remarkable progress, conventional recommendation models (CRM) still have some limitations, e.g., lacking open-world knowledge, and difficulties in comprehending users' underlying preferences and motivations. Meanwhile, large language models (LLM) have shown impressive general intelligence and human-like capabilities, which mainly stem from their extensive open-world knowledge, reasoning ability, as well as their comprehension of human culture and society. Consequently, the emergence of LLM is inspiring the design of recommender systems and pointing out a promising research direction, i.e., whether we can incorporate LLM and benefit from their knowledge and capabilities to compensate for the limitations of CRM. In this paper, we conduct a comprehensive survey on this research direction from the perspective of the whole pipeline in real-world recommender systems. Specifically, we summarize existing works from two orthogonal aspects: where and how to adapt LLM to RS. For the WHERE question, we discuss the roles that LLM could play in different stages of the recommendation pipeline, i.e., feature engineering, feature encoder, scoring/ranking function, user interaction, and pipeline controller. For the HOW question, we investigate the training and inference strategies, resulting in two fine-grained taxonomy criteria, i.e., whether to tune LLM or not, and whether to involve conventional recommendation models for inference. Then, we highlight key challenges in adapting LLM to RS from three aspects, i.e., efficiency, effectiveness, and ethics. Finally, we summarize the survey and discuss the future prospects. We actively maintain a GitHub repository for papers and other related resources: https://github.com/CHIANGEL/Awesome-LLM-for-RecSys/.

翻译：随着在线服务的快速发展，推荐系统（RS）对于缓解信息过载问题已变得日益不可或缺。尽管取得了显著进展，传统推荐模型（CRM）仍存在一些局限性，例如缺乏开放世界知识，以及难以理解用户的深层偏好和动机。与此同时，大语言模型（LLM）展现出令人印象深刻的通用智能和类人能力，这主要源于其广泛的开放世界知识、推理能力以及对人类文化和社会的理解。因此，LLM的出现正在启发推荐系统的设计，并指出了一个极具前景的研究方向，即我们能否引入LLM，并利用其知识与能力来弥补CRM的不足。本文从实际推荐系统全流程的视角，对这一研究方向进行了全面综述。具体而言，我们从两个正交维度总结了现有工作：在何处以及如何将LLM适配到RS中。针对“何处”的问题，我们探讨了LLM在推荐流程不同阶段可能扮演的角色，即特征工程、特征编码器、评分/排序函数、用户交互以及流程控制器。针对“如何”的问题，我们研究了训练与推理策略，由此得出两个细粒度的分类标准：是否对LLM进行微调，以及推理时是否涉及传统推荐模型。随后，我们从效率、效果和伦理三个方面，重点阐述了将LLM适配到RS中的关键挑战。最后，我们对本综述进行了总结并展望了未来前景。我们积极维护一个GitHub仓库，用于收录相关论文及其他资源：https://github.com/CHIANGEL/Awesome-LLM-for-RecSys/。