LiteRAG：低成本图检索增强生成方法
LiteRAG: Cost-Efficient Graph-Based Retrieval-Augmented Generation
清华团队推出LiteRAG，比GraphRAG快100倍且便宜99%，多跳问答更高效。
LiteRAG是一种基于图的检索方法，在DistComp基准测试中达到0.798的最高质量，查询延迟降低100倍以上，成本减少99%。在UltraDomain测试中，与LinearRAG质量相当但使用token数量减少约14倍。研究显示查询自适应阈值和社区感知中心惩罚是提高token效率的关键因素。
LiteRAG: Cost-Efficient Graph-Based Retrieval-Augmented Generation
Graph-based retrieval can improve multi-hop question answering, but existing approaches often incur high query-time costs and produce diffuse, oversized contexts that reduce generation efficiency. We present LiteRAG, a graph-based retrieval method that replaces expensive retrieval-time LLM control with query-conditioned algorithmic exploration and reasoning-chain context construction. On DistComp, a benchmark for multi-hop retrieval over distributed-systems papers, LiteRAG attains the highest overall quality among the evaluated methods (0.798) while reducing per-query latency by over 100$\times$ and cost by over 99% relative to GraphRAG Global and DRIFT. On UltraDomain, it matches LinearRAG on overall quality while using about 14$\times$ fewer tokens. An ablation study indicates that LiteRAG's query-adaptive thresholding and community-aware hub penalization are the main drivers of its token-efficiency gains.