Empowering Few-Shot Recommender Systems with Large Language Models -- Enhanced Representations

TL;DR

This paper explores how large language models can be integrated into recommender systems to improve their performance in few-shot scenarios by generating user and item representations from explicit feedback.

Contribution

It introduces a prompting template to generate representations from LLMs and demonstrates their effectiveness across various recommendation tasks.

Findings

LLMs improve recommendation performance in few-shot settings.

The proposed method enhances generalization of recommender systems.

Ablation studies confirm the importance of LLM-processed representations.

Abstract

Recommender systems utilizing explicit feedback have witnessed significant advancements and widespread applications over the past years. However, generating recommendations in few-shot scenarios remains a persistent challenge. Recently, large language models (LLMs) have emerged as a promising solution for addressing natural language processing (NLP) tasks, thereby offering novel insights into tackling the few-shot scenarios encountered by explicit feedback-based recommender systems. To bridge recommender systems and LLMs, we devise a prompting template that generates user and item representations based on explicit feedback. Subsequently, we integrate these LLM-processed representations into various recommendation models to evaluate their significance across diverse recommendation tasks. Our ablation experiments and case study analysis collectively demonstrate the effectiveness of LLMs in processing explicit feedback, highlighting that LLMs equipped with generative and logical reasoning capabilities can effectively serve as a component of recommender systems to enhance their performance in few-shot scenarios. Furthermore, the broad adaptability of LLMs augments the generalization potential of recommender models, despite certain inherent constraints. We anticipate that our study can inspire researchers to delve deeper into the multifaceted dimensions of LLMs's involvement in recommender systems and contribute to the advancement of the explicit feedback-based recommender systems field.