[论文解读] Recommender Systems in the Era of Large Language Models (LLMs)

Zihuai Zhao, Wenqi Fan+9 more|arXiv (Cornell University)|Jul 5, 2023

Topic Modeling被引用 29

一句话总结

本论文提供了对大语言模型如何集成到推荐系统的全面综述，涵盖预训练、微调和提示范式，并勾勒未来方向。

ABSTRACT

With the prosperity of e-commerce and web applications, Recommender Systems (RecSys) have become an important component of our daily life, providing personalized suggestions that cater to user preferences. While Deep Neural Networks (DNNs) have made significant advancements in enhancing recommender systems by modeling user-item interactions and incorporating textual side information, DNN-based methods still face limitations, such as difficulties in understanding users' interests and capturing textual side information, inabilities in generalizing to various recommendation scenarios and reasoning on their predictions, etc. Meanwhile, the emergence of Large Language Models (LLMs), such as ChatGPT and GPT4, has revolutionized the fields of Natural Language Processing (NLP) and Artificial Intelligence (AI), due to their remarkable abilities in fundamental responsibilities of language understanding and generation, as well as impressive generalization and reasoning capabilities. As a result, recent studies have attempted to harness the power of LLMs to enhance recommender systems. Given the rapid evolution of this research direction in recommender systems, there is a pressing need for a systematic overview that summarizes existing LLM-empowered recommender systems, to provide researchers in relevant fields with an in-depth understanding. Therefore, in this paper, we conduct a comprehensive review of LLM-empowered recommender systems from various aspects including Pre-training, Fine-tuning, and Prompting. More specifically, we first introduce representative methods to harness the power of LLMs (as a feature encoder) for learning representations of users and items. Then, we review recent techniques of LLMs for enhancing recommender systems from three paradigms, namely pre-training, fine-tuning, and prompting. Finally, we comprehensively discuss future directions in this emerging field.

研究动机与目标

• 通过识别基于DNN的推荐系统在理解文本和对未见任务的泛化方面的局限性来推动研究。
• 总结 LLMs 如何提升对用户和项的表示学习。
• 将文献组织成预训练、微调和提示范式，为未来研究与实践提供指南。
• 讨论利用 LLMs 进行 RecSys 的挑战与未来方向。

提出的方法

• 将现有的 LLM 驱动的推荐系统分为基于 ID 的方法和以文本侧信息增强的方法，并进行分类。
• 在三个范式下总结基于 LLM 的技术：预训练、微调和提示。
• 突出具有代表性的方法和任务，如评分预测、序列化推荐，以及可解释/对话式推荐。
• 讨论方法学方面，如索引方案、适配器和基于提示的学习。
• 识别挑战并提出未来研究方向。

实验结果

研究问题

• RQ1 在 RecSys 中，LLMs 用来学习用户/项表示的代表性方式有哪些（基于ID 还是文本侧信息）？
• RQ2 预训练、微调和提示范式如何提升 RecSys 的性能与能力？
• RQ3 将 LLMs 融入推荐系统的主要挑战与有前景的方向是什么？

主要发现

• LLMs 能实现更丰富的语言理解和推理，以支持超越传统基于 ID 的方法的推荐任务。
• 三大范式——预训练、微调和提示——构成将 LLMs 适配到 RecSys 的核心工具箱。
• 提示技术、上下文内学习和思维链式提示可以提升推荐中的推理能力和可解释性。
• 微调策略从全量模型到参数高效方法，平衡性能与计算成本。
• 文本侧信息在某些设置下可以补充或超越基于 ID 的表示，从而在跨任务上实现更好的泛化。