Enhancing LLM-based Recommendation with Preference Hint Discovery from Knowledge Graph

TL;DR

This paper introduces a novel method to improve LLM-based recommendation systems by selectively extracting and organizing preference hints from knowledge graphs, leading to better handling of complex preferences and unseen items.

Contribution

It proposes a preference hint discovery model that combines knowledge graph insights with an attention mechanism to enhance LLM recommendations, addressing prior limitations.

Findings

Achieved over 3.02% relative improvement in recommendation accuracy.

Effectively extracts and organizes preference hints for unseen items.

Demonstrated robustness across pair-wise and list-wise tasks.

Abstract

LLMs have garnered substantial attention in recommendation systems. Yet they fall short of traditional recommenders when capturing complex preference patterns. Recent works have tried integrating traditional recommendation embeddings into LLMs to resolve this issue, yet a core gap persists between their continuous embedding and discrete semantic spaces. Intuitively, textual attributes derived from interactions can serve as critical preference rationales for LLMs' recommendation logic. However, directly inputting such attribute knowledge presents two core challenges: (1) Deficiency of sparse interactions in reflecting preference hints for unseen items; (2) Substantial noise introduction from treating all attributes as hints. To this end, we propose a preference hint discovery model based on the interaction-integrated knowledge graph, enhancing LLM-based recommendation. It utilizes traditional recommendation principles to selectively extract crucial attributes as hints. Specifically, we design a collaborative preference hint extraction schema, which utilizes semantic knowledge from similar users' explicit interactions as hints for unseen items. Furthermore, we develop an instance-wise dual-attention mechanism to quantify the preference credibility of candidate attributes, identifying hints specific to each unseen item. Using these item- and user-based hints, we adopt a flattened hint organization method to shorten input length and feed the textual hint information to the LLM for commonsense reasoning. Extensive experiments on both pair-wise and list-wise recommendation tasks verify the effectiveness of our proposed framework, indicating an average relative improvement of over 3.02% against baselines.