Knowledge Graph Enhanced Language Agents for Recommendation

TL;DR

This paper introduces KGLA, a framework that enhances language agents for recommendation systems by integrating Knowledge Graphs, capturing complex user-item relationships to improve recommendation accuracy significantly.

Contribution

The paper proposes KGLA, a novel framework combining language agents with Knowledge Graphs to better understand user-item relationships for improved recommendations.

Findings

KGLA significantly boosts recommendation performance, with a 33%-95% increase in NDCG@1.

Using KG paths as natural language descriptions enhances agent interaction and understanding.

Experimental results outperform previous baseline methods on multiple benchmarks.

Abstract

Language agents have recently been used to simulate human behavior and user-item interactions for recommendation systems. However, current language agent simulations do not understand the relationships between users and items, leading to inaccurate user profiles and ineffective recommendations. In this work, we explore the utility of Knowledge Graphs (KGs), which contain extensive and reliable relationships between users and items, for recommendation. Our key insight is that the paths in a KG can capture complex relationships between users and items, eliciting the underlying reasons for user preferences and enriching user profiles. Leveraging this insight, we propose Knowledge Graph Enhanced Language Agents(KGLA), a framework that unifies language agents and KG for recommendation systems. In the simulated recommendation scenario, we position the user and item within the KG and integrate KG paths as natural language descriptions into the simulation. This allows language agents to interact with each other and discover sufficient rationale behind their interactions, making the simulation more accurate and aligned with real-world cases, thus improving recommendation performance. Our experimental results show that KGLA significantly improves recommendation performance (with a 33%-95% boost in NDCG@1 among three widely used benchmarks) compared to the previous best baseline method.