Personalized Graph-Based Retrieval for Large Language Models

TL;DR

This paper introduces PGraphRAG, a novel framework that uses user knowledge graphs to improve personalized responses in large language models, especially in cold-start scenarios with limited user data.

Contribution

The paper presents PGraphRAG, a new graph-based retrieval method that enhances personalization in LLMs by integrating structured user knowledge, and introduces a benchmark for evaluating such personalized text generation.

Findings

PGraphRAG outperforms existing personalization methods across multiple tasks.

The framework improves contextual understanding and output quality in cold-start scenarios.

Experimental results validate the effectiveness of graph-based retrieval for personalization.

Abstract

As large language models (LLMs) evolve, their ability to deliver personalized and context-aware responses offers transformative potential for improving user experiences. Existing personalization approaches, however, often rely solely on user history to augment the prompt, limiting their effectiveness in generating tailored outputs, especially in cold-start scenarios with sparse data. To address these limitations, we propose Personalized Graph-based Retrieval-Augmented Generation (PGraphRAG), a framework that leverages user-centric knowledge graphs to enrich personalization. By directly integrating structured user knowledge into the retrieval process and augmenting prompts with user-relevant context, PGraphRAG enhances contextual understanding and output quality. We also introduce the Personalized Graph-based Benchmark for Text Generation, designed to evaluate personalized text generation tasks in real-world settings where user history is sparse or unavailable. Experimental results show that PGraphRAG significantly outperforms state-of-the-art personalization methods across diverse tasks, demonstrating the unique advantages of graph-based retrieval for personalization.