mlsanityData to 14 Oct 2026

TERAG: Token-Efficient Graph-Based Retrieval-Augmented Generation

arXiv 2509.18667 ↗First posted 23 Sep 2025cs.AIcited by 2

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

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.

Key facts. Cited by 2 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 32 references that are in the map. First posted on arXiv 23 Sep 2025.

Builds on

23 of 32 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG13 Feb
  2. 2025MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation12 Jan
  3. 2024LightRAG: Simple and Fast Retrieval-Augmented Generation8 Oct
  4. 2024Graph Retrieval-Augmented Generation: A Survey15 Aug
  5. 2024GRAG: Graph Retrieval-Augmented Generation26 May
  6. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr

Other references · 17

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2019Language Models as Knowledge Bases?cited by 1,936
  5. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  6. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  7. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 238
  8. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 231
  9. 2024A Survey on Efficient Inference for Large Language Modelscited by 205
  10. 2020The Next Decade in AI: Four Steps Towards Robust Artificial Intelligencecited by 195
  11. 2024GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theorycited by 37
  12. 2024A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directionscited by 34
5 more
  1. 2023DB-GPT: Empowering Database Interactions with Private Large Language Modelscited by 27
  2. 2025AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corporacited by 23
  3. 2022COPEN: Probing Conceptual Knowledge in Pre-trained Language Modelscited by 21
  4. 2024Generative AI in Education: A Study of Educators' Awareness, Sentiments, and Influencing Factorscited by 10
  5. 2024Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answeringcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Democratizing GraphRAG: Linear, CPU-Only Graph Retrieval for Multi-Hop QAcited by 0
  2. 2026Verifiable Retrieval for Legal Reasoning through Structure-driven Knowledge Graphcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes
  2. 2025In-depth Analysis of Graph-based RAG in a Unified Framework
  3. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey
  4. 2026DA-RAG: Dynamic Attributed Community Search for Retrieval-Augmented Generation
  5. 2025AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMs
  6. 2026Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs
  7. 2025RAG vs. GraphRAG: A Systematic Evaluation and Key Insights
  8. 2025Query-Centric Graph Retrieval Augmented Generation