# KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG

arXiv: https://arxiv.org/abs/2502.09304 · HTML: https://mlsanity.com/paper/2502.09304/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Placed in

- Retrieval-augmented generation / [Knowledge-graph and structured-knowledge RAG](https://mlsanity.com/rag/knowledge-graph-and-structured-knowledge-rag/)

## Builds on (most cited first, 23 of 23)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [Knowledge Graph Prompting for Multi-Document Question Answering](https://mlsanity.com/paper/2308.11730/) (2023)
- [Evaluation of Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2405.07437/) (2024)
- [Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs](https://mlsanity.com/paper/2404.07103/) (2024)
- [Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering](https://mlsanity.com/paper/2404.17723/) (2024)
- [HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction](https://mlsanity.com/paper/2408.04948/) (2024)
- [DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer's Disease Questions with Scientific Literature](https://mlsanity.com/paper/2405.04819/) (2024)
- [RareBench: Can LLMs Serve as Rare Diseases Specialists?](https://mlsanity.com/paper/2402.06341/) (2024)
- [RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering](https://mlsanity.com/paper/2407.13998/) (2024)
- [HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications](https://mlsanity.com/paper/2409.09046/) (2024)
- [Graph-Based Retriever Captures the Long Tail of Biomedical Knowledge](https://mlsanity.com/paper/2402.12352/) (2024)
- [ATLANTIC: Structure-Aware Retrieval-Augmented Language Model for Interdisciplinary Science](https://mlsanity.com/paper/2311.12289/) (2023)
- [EWEK-QA: Enhanced Web and Efficient Knowledge Graph Retrieval for Citation-based Question Answering Systems](https://mlsanity.com/paper/2406.10393/) (2024)
- [RETE: Retrieval-Enhanced Temporal Event Forecasting on Unified Query Product Evolutionary Graph](https://mlsanity.com/paper/2202.06129/) (2022)
- [CompanyKG: A Large-Scale Heterogeneous Graph for Company Similarity Quantification](https://mlsanity.com/paper/2306.10649/) (2023)
- [Leveraging Knowledge Graphs and LLMs to Support and Monitor Legislative Systems](https://mlsanity.com/paper/2409.13252/) (2024)

## Built on by (most cited first, 29 of 29)

- [When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2506.05690/) (2025)
- [In-depth Analysis of Graph-based RAG in a Unified Framework](https://mlsanity.com/paper/2503.04338/) (2025)
- [ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.09891/) (2025)
- [Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval](https://mlsanity.com/paper/2509.21710/) (2025)
- [Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding](https://mlsanity.com/paper/2510.15253/) (2025)
- [Clue-RAG: Towards Accurate and Cost-Efficient Graph-based RAG via Multi-Partite Graph and Query-Driven Iterative Retrieval](https://mlsanity.com/paper/2507.08445/) (2025)
- [C2KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference](https://mlsanity.com/paper/2607.17715/) (2026)
- [Query-Efficient Agentic Graph Extraction Attacks on GraphRAG Systems](https://mlsanity.com/paper/2601.14662/) (2026)
- [How Significant Are the Real Performance Gains? An Unbiased Evaluation Framework for GraphRAG](https://mlsanity.com/paper/2506.06331/) (2025)
- [TERAG: Token-Efficient Graph-Based Retrieval-Augmented Generation](https://mlsanity.com/paper/2509.18667/) (2025)
- [EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval](https://mlsanity.com/paper/2604.17458/) (2026)
- [VikingMem: A Memory Base Management System for Stateful LLM-based Applications](https://mlsanity.com/paper/2605.29640/) (2026)
- [RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA](https://mlsanity.com/paper/2510.20505/) (2025)
- [TagRAG: Tag-guided Hierarchical Knowledge Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.05254/) (2025)
- [MG2-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2604.04969/) (2026)
- [SEAM: Shot Entity-Attribute Memory for Consistent Short-Drama Generation at Scale](https://mlsanity.com/paper/2608.22725/) (2026)
- [Graph-Guided Concept Selection for Efficient Retrieval-Augmented Generation](https://mlsanity.com/paper/2510.24120/) (2025)
- [GraFine: Retrieval-Time Refinement for Efficient Graph RAG over Corpus Graphs](https://mlsanity.com/paper/2601.18579/) (2026)
- [CLEAR: Context Augmentation from Contrastive Learning of Experience via Agentic Reflection](https://mlsanity.com/paper/2604.07487/) (2026)
- [AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation](https://mlsanity.com/paper/2604.20844/) (2026)
- [ASTRA-QA: A Benchmark for Abstract Question Answering over Documents](https://mlsanity.com/paper/2605.10168/) (2026)
- [Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answering](https://mlsanity.com/paper/2606.10921/) (2026)
- [CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval](https://mlsanity.com/paper/2606.28365/) (2026)
- [PolyUQuest: Verifiable Structure-Aware Web RAG over Heterogeneous Graphs](https://mlsanity.com/paper/2607.08269/) (2026)
- [Optimizing Hypergraph-Based RAG: Toward Better Fact Extraction and Chunk Retrieval](https://mlsanity.com/paper/2607.20506/) (2026)
- [PreGress: Ranking-Native Pre-training and Prompting for Graph Node Ranking](https://mlsanity.com/paper/2608.09016/) (2026)
- [The Commercial Tax: Rent-vs-Own Blind Spots in Multi-Hop Retrieval Benchmarks](https://mlsanity.com/paper/2608.16096/) (2026)
- [LiteRAG: Cost-Efficient Graph-Based Retrieval-Augmented Generation](https://mlsanity.com/paper/2609.10239/) (2026)
- [ConRAG: Lightweight inference of multi-hop relations](https://mlsanity.com/paper/2609.35193/) (2026)

## Abstract (arXiv)

Graph-RAG constructs a knowledge graph from text chunks to improve retrieval in Large Language Model (LLM)-based question answering. It is particularly useful in domains such as biomedicine, law, and political science, where retrieval often requires multi-hop reasoning over proprietary documents. Some existing Graph-RAG systems construct KNN graphs based on text chunk relevance, but this coarse-grained approach fails to capture entity relationships within texts, leading to sub-par retrieval and generation quality. To address this, recent solutions leverage LLMs to extract entities and relationships from text chunks, constructing triplet-based knowledge graphs. However, this approach incurs significant indexing costs, especially for large document collections. To ensure a good result accuracy while reducing the indexing cost, we propose KET-RAG, a multi-granular indexing framework. KET-RAG first identifies a small set of key text chunks and leverages an LLM to construct a knowledge graph skeleton. It then builds a text-keyword bipartite graph from all text chunks, serving as a lightweight alternative to a full knowledge graph. During retrieval, KET-RAG searches both structures: it follows the local search strategy of existing Graph-RAG systems on the skeleton while mimicking this search on the bipartite graph to improve retrieval quality. We evaluate 13 solutions on three real-world datasets, demonstrating that KET-RAG outperforms all competitors in indexing cost, retrieval effectiveness, and generation quality. Notably, it achieves comparable or superior retrieval quality to Microsoft's Graph-RAG while reducing indexing costs by over an order of magnitude. Additionally, it improves the generation quality by up to 32.4% while lowering indexing costs by around 20%.