Recommender systems (RS) play important roles to match users' information needs for Internet applications. In natural language processing (NLP) domains, large language model (LLM) has shown astonishing emergent abilities (e.g., instruction following, reasoning), thus giving rise to the promising research direction of adapting LLM to RS for performance enhancements and user experience improvements. In this paper, we conduct a comprehensive survey on this research direction from an application-oriented view. We first summarize existing research works from two orthogonal perspectives: 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, 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 LLMs or not, and whether to involve conventional recommendation model (CRM) for inference. Detailed analysis and general development trajectories are provided for both questions, respectively. 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 also actively maintain a GitHub repository for papers and other related resources in this rising direction: https://github.com/CHIANGEL/Awesome-LLM-for-RecSys.

翻译：推荐系统（RS）在互联网应用中扮演着匹配用户信息需求的重要角色。在自然语言处理（NLP）领域，大型语言模型（LLM）展现出惊人的涌现能力（如指令遵循、推理），由此催生了将LLM适配至推荐系统以提升性能与用户体验这一具有前景的研究方向。本文从应用导向视角对该研究方向进行系统性综述。我们首先从两个正交维度总结现有研究工作：LLM适配推荐系统的"位置"与"方式"。针对"位置"问题，我们探讨LLM在推荐流水线不同阶段可扮演的角色，即特征工程、特征编码器、评分/排序函数及流水线控制器。针对"方式"问题，我们深入分析训练与推理策略，提出两个细粒度分类标准：是否微调LLM、以及是否引入传统推荐模型（CRM）进行推理。针对两类问题分别提供详细分析与发展轨迹。继而从效率、效果与伦理三个维度阐明LLM适配推荐系统的关键挑战。最后总结全文并展望未来方向。我们持续维护该前沿方向的论文与资源GitHub仓库：https://github.com/CHIANGEL/Awesome-LLM-for-RecSys。