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）在匹配互联网应用中的用户信息需求方面发挥着重要作用。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（例如指令遵循、推理），因此催生了将LLM适配到RS中以提升性能并改善用户体验这一有前景的研究方向。本文从应用视角对该研究方向进行了全面综述。我们首先从两个正交角度总结现有研究工作：何处（Where）以及如何（How）将LLM适配至RS。针对“Where”问题，我们探讨了LLM在推荐管道不同阶段（即特征工程、特征编码器、评分/排序函数及管道控制器）扮演的角色。针对“How”问题，我们分析了训练与推理策略，构建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。针对上述两个问题，我们分别提供了详细分析及通用发展轨迹。接着，我们从效率、有效性和伦理性三个层面突出了将LLM适配至RS的关键挑战。最后，我们总结综述并展望未来前景。我们还在GitHub仓库中持续维护该新兴方向的相关论文与资源：https://github.com/CHIANGEL/Awesome-LLM-for-RecSys。