Efficient and Deployable Knowledge Infusion for Open-World Recommendations via Large Language Models

TL;DR

This paper introduces REKI, a knowledge infusion framework that leverages large language models to enhance open-world recommendations efficiently, achieving better performance and deployment feasibility in industrial systems.

Contribution

REKI presents a novel method for extracting and condensing external knowledge from LLMs, improving recommendation accuracy while reducing resource consumption and inference latency.

Findings

REKI outperforms state-of-the-art baselines in experiments.

REKI improves online recommendation performance by 7% and 1.99%.

The framework is compatible with various recommendation models.

Abstract

Recommender systems (RSs) play a pervasive role in today's online services, yet their closed-loop nature constrains their access to open-world knowledge. Recently, large language models (LLMs) have shown promise in bridging this gap. However, previous attempts to directly implement LLMs as recommenders fall short in meeting the requirements of industrial RSs, particularly in terms of online inference latency and offline resource efficiency. Thus, we propose REKI to acquire two types of external knowledge about users and items from LLMs. Specifically, we introduce factorization prompting to elicit accurate knowledge reasoning on user preferences and items. We develop individual knowledge extraction and collective knowledge extraction tailored for different scales of scenarios, effectively reducing offline resource consumption. Subsequently, generated knowledge undergoes efficient transformation and condensation into augmented vectors through a hybridized expert-integrated network, ensuring compatibility. The obtained vectors can then be used to enhance any conventional recommendation model. We also ensure efficient inference by preprocessing and prestoring the knowledge from LLMs. Experiments demonstrate that REKI outperforms state-of-the-art baselines and is compatible with lots of recommendation algorithms and tasks. Now, REKI has been deployed to Huawei's news and music recommendation platforms and gained a 7% and 1.99% improvement during the online A/B test.