LiteRAG: Cost-Efficient Graph-Based Retrieval-Augmented Generation

arXiv:2609.10239v1 Announce Type: cross Abstract: 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 100imes and cost by over 99% relative to GraphRAG Global and DRIFT. On UltraDomain, it matches LinearRAG on overall quality while using about 14imes 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.

Related

• A Storage-Retrieval Gap in Parametric Knowledge Graph Memory
• Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)
• MissDiag: Diagnostic Evaluation of Incomplete-Knowledge Robustness in KGQA and KG-RAG
• ConRAG: Consensus-Driven Multi-View Retrieval for Multi-Hop Question Answering
• When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering

Source: arXiv cs.CL | 2026-09-10