大型語言模型的個性化基於圖形的檢索

Personalized Graph-Based Retrieval for Large Language Models

January 4, 2025

作者: Steven Au, Cameron J. Dimacali, Ojasmitha Pedirappagari, Namyong Park, Franck Dernoncourt, Yu Wang, Nikos Kanakaris, Hanieh Deilamsalehy, Ryan A. Rossi, Nesreen K. Ahmed

cs.AI

摘要

隨著大型語言模型（LLMs）的演進，它們提供個性化和上下文感知回應的能力，為改善使用者體驗帶來轉變性潛力。然而，現有的個性化方法通常僅依賴使用者歷史來增強提示，這限制了它們在生成定制輸出方面的效果，特別是在具有稀疏數據的冷啟動情況下。為了解決這些限制，我們提出了基於個性化圖檢索增強生成（PGraphRAG）的框架，該框架利用以使用者為中心的知識圖來豐富個性化。通過將結構化的使用者知識直接整合到檢索過程中，並用使用者相關上下文來增強提示，PGraphRAG提升了上下文理解和輸出質量。我們還介紹了基於個性化圖的文本生成基準，旨在評估在使用者歷史稀疏或不可用的現實世界環境中的個性化文本生成任務。實驗結果顯示，PGraphRAG在各種任務上顯著優於最先進的個性化方法，展示了基於圖檢索用於個性化的獨特優勢。

English

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.