arXiv Artificial Intelligence

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

1 hour ago 11.09.2026 07:00 👁 1 views
LiteRAG: Cost-Efficient Graph-Based Retrieval-Augmented Generation

Quick summary

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)

Key takeaways

  • 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)

Why it matters

“LiteRAG: Cost-Efficient Graph-Based Retrieval-Augmented Generation” highlights the need for repeatable measurement rather than a single impressive demonstration. Independent validation across datasets and clearly stated limitations determine whether a result can guide product decisions.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗