Personalized Graph-Based Retrieval for Large Language Models
Graph-based retrieval publication on personalization for large language models, centered on the PGraphRAG framework and benchmark.
Collaborators
As large language models continue to evolve, their ability to deliver personalized, context-aware responses holds significant promise for user experience. Most existing personalization approaches rely solely on user history, which limits effectiveness in cold-start and sparse-data scenarios. We introduce Personalized Graph-based Retrieval-Augmented Generation (PGraphRAG), a framework that enhances personalization by leveraging user-centric knowledge graphs. By integrating structured user information into retrieval and augmenting prompts with graph-based context, PGraphRAG improves both relevance and generation quality. We also present the Personalized Graph-based Benchmark for Text Generation, designed to evaluate personalized generation in settings where user history is minimal. Experimental results show average ROUGE-1 gains of 14.8% on long-text and 4.6% on short-text generation over prior methods.