用极少的令牌开销实现高效图检索增强生成。
TERAG: Token-Efficient Graph-Based Retrieval-Augmented Generation
- 基于个性化PageRank构建低消耗信息图
- 精度达主流方法80%以上，令牌消耗仅3%-11%
- 适合大规模、成本敏感的部署场景
基于图的检索增强生成（RAG）已成为提升大语言模型（LLMs）推理能力、准确性和事实性的重要方法。然而，现有许多基于图的RAG系统在图构建阶段忽视了大语言模型带来的高令牌开销，限制了其大规模应用。为此，我们提出TERAG——一种简单但高效的框架，在显著降低开销的同时构建有信息量的图。受HippoRAG启发，我们在检索阶段引入个性化PageRank（PPR），在仅使用3%-11%输出令牌的情况下，达到主流图基RAG方法至少80%的精度。凭借极低的令牌开销和高效的构建流程，TERAG非常适合大规模及成本敏感的应用场景。
原文摘要 · Abstract (English)
Graph-based Retrieval-augmented generation (RAG) has become a widely studied approach for improving the reasoning, accuracy, and factuality of Large Language Models (LLMs). However, many existing graph-based RAG systems overlook the high cost associated with LLM token usage during graph construction, hindering large-scale adoption. To address this, we propose TERAG, a simple yet effective framework designed to build informative graphs at a significantly lower cost. Inspired by HippoRAG, we incorporate Personalized PageRank (PPR) during the retrieval phase, and we achieve at least 80% of the accuracy of widely used graph-based RAG methods while consuming only 3%-11% of the output tokens. With its low token footprint and efficient construction pipeline, TERAG is well-suited for large-scale and cost-sensitive deployment scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。