Recommender Systems in the Era of Large Language Models (LLMs)

By Wenqi Fan, Zihuai Zhao, Jiatong Li, Yunqing Liu, Xiaowei Mei, Yiqi Wang, Jiliang Tang, Qing Li. IEEE Transactions on Knowledge and Data Engineering, 2023

541 citations recorded by the source corpus.

With the prosperity of e-commerce and web applications, Recommender Systems (RecSys) have become an indispensable and important component, providing personalized suggestions that cater to user preferences. While Deep Neural Networks (DNNs) have achieved significant advancements in enhancing recommender systems, these DNN-based methods still exhibit some limitations, such as inferior capabilities to effectively capture textual side information about users and items, difficulties in generalization to various recommendation scenarios, and reasoning on their predictions, etc. Meanwhile, the development of Large Language Models (LLMs), such as ChatGPT and GPT-4, 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 capabilities and reasoning skills. As a result, recent studies have actively 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. Therefore, in this survey, we comprehensively review LLM-empowered recommender systems from various perspectives including pre-training, fine-tuning, and prompting paradigms. More specifically, we first introduce the representative methods to learn user and item representations, leveraging LLMs as feature encoders. Then, we systematically review the emerging advanced techniques of LLMs for enhancing recommender systems from three paradigms, namely pre-training, fine-tuning, and prompting. Finally, we comprehensively discuss the promising future directions in this emerging field.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/a35f1315e91513ff0bec0c488fe175214fd9636c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Wayne Xin Zhao
2. Jiliang Tang
3. Yupeng Hou
4. Hongyu Lu
5. Ruobing Xie
6. Dawei Yin
7. Junjie Zhang
8. Julian McAuley

In Information Systems

1. Wayne Xin Zhao
2. Yupeng Hou
3. Hongyu Lu
4. Chao Huang
5. Jiliang Tang
6. Lianghao Xia
7. Zihan Lin
8. Dawei Yin

Citations in the corpus

• Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach (2023, unknown): “Compared to long-term preferences, users’ intentions refer to their more immediate demands for certain types of items, which may be different from user long-term preferences.”
• Large Language Models for Software Engineering: A Systematic Literature Review (2023, background): “Simultaneously, researchers have embarked on a series of research activities regarding LLMrelated works, where a number of literature reviews or survey papers have been produced [29, 58, 59, 338].”
• Evaluating Large Language Models in Class-Level Code Generation (2024, background): “To date, the evaluation for LLMs has covered a wide range [20], encompassing not only traditional NLP tasks ( e.g., sentiment analysis [17], question answering [16], and reasoning [19]) but also some specific downstream domains ( e.g., medicine [23], agent [34] and recommendation system [28]).”
• Large Language Models for Information Retrieval: A Survey (2023, unknown): “The term “document” will henceforth refer to any text-based content subject to retrieve, including both long articles and short passages.”
• Exploring the Potential of Large Language Models (LLMs)in Learning on Graphs (2023, methodology): “Following our proposed two pipelines, i.e., LLMs as the En-hancers and LLMs as the Predictors, we review existing works in this section.”
• A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models (2024, unknown): “These technical improvements lead to the emergence of remarkable capabilities of LLMs [37, 157], particularly in language understanding and generation, in-context learning, and other aspects.”
• How Can Recommender Systems Benefit from Large Language Models: A Survey (2023, unknown): “Finally, Section 5 concludes this survey and draws a hopeful vision for future prospects in research communities of LLM-enhanced recommender systems.”
• When large language models meet personalization: perspectives of challenges and opportunities (2023, unknown): “Fan et al [7], on the other hand, conduct a review with a focus on pre-training, fine-tuning, and prompting approaches.”
• Large Language Models are Zero-Shot Rankers for Recommender Systems (2023, background): “As the scaling law shows, the performance of LLMs on various downstream tasks generally increases while scaling up the model size and the amount of training data [24, 15, 28].”
• Representation Learning with Large Language Models for Recommendation (2023, result): “It is evident from the results in Figure 1 that the recommendations refined by the ChatGPT perform worse than the original results provided by LightGCN.”
• LLMs Are Also Effective Embedding Models: An In-depth Overview (2024, unknown): “Embeddings are crucial in modern deep learning literature because they enable efficient representation of high-dimensional data in a compact, dense format [59].”