Personalized Graph-Based Retrieval for Large Language Models

2025-01-04

AI Summary

To address the limited personalization capability of large language models (LLMs) in user cold-start and historically sparse scenarios, this paper proposes PGraphRAG—a retrieval-augmented generation framework grounded in user knowledge graphs. Its core innovation is the first user-centric, knowledge-graph-driven personalized retrieval paradigm, which explicitly integrates structured user knowledge throughout both retrieval and prompt construction. We further design a graph neural network-guided mechanism for adaptive retrieval and personalized context fusion. Additionally, we introduce the first benchmark for personalized text generation tailored to sparse-history settings. Extensive experiments demonstrate that PGraphRAG significantly outperforms existing state-of-the-art methods across multiple tasks: under cold-start conditions, it achieves 23.6% and 19.8% improvements in BLEU-4 and BERTScore, respectively.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Generation
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Personalized Responses
• Insufficient User History
• Large Language Models

Innovation

• PGraphRAG
• Personalized Knowledge Graph
• Enhanced Personalization