LLM-I2I: Boost Your Small Item2Item Recommendation Model with Large Language Model

TL;DR

This paper introduces LLM-I2I, a data-centric framework that uses large language models to generate and filter training data, significantly improving item-to-item recommendation accuracy, especially for long-tail items, without changing model architectures.

Contribution

The paper presents a novel LLM-based data augmentation and filtering framework that enhances I2I recommendation performance by addressing data sparsity and noise issues.

Findings

Improves recommendation accuracy for long-tail items.

Boosts recall number (RN) by 6.02% and GMV by 1.22% in real deployment.

Effectively mitigates data quality issues using LLMs without altering models.

Abstract

Item-to-Item (I2I) recommendation models are widely used in real-world systems due to their scalability, real-time capabilities, and high recommendation quality. Research to enhance I2I performance focuses on two directions: 1) model-centric approaches, which adopt deeper architectures but risk increased computational costs and deployment complexity, and 2) data-centric methods, which refine training data without altering models, offering cost-effectiveness but struggling with data sparsity and noise. To address these challenges, we propose LLM-I2I, a data-centric framework leveraging Large Language Models (LLMs) to mitigate data quality issues. LLM-I2I includes (1) an LLM-based generator that synthesizes user-item interactions for long-tail items, alleviating data sparsity, and (2) an LLM-based discriminator that filters noisy interactions from real and synthetic data. The refined data is then fused to train I2I models. Evaluated on industry (AEDS) and academic (ARD) datasets, LLM-I2I consistently improves recommendation accuracy, particularly for long-tail items. Deployed on a large-scale cross-border e-commerce platform, it boosts recall number (RN) by 6.02% and gross merchandise value (GMV) by 1.22% over existing I2I models. This work highlights the potential of LLMs in enhancing data-centric recommendation systems without modifying model architectures.